Consumer-grade EEG is entering everyday devices, from earbuds to headbands, raising the question of whether language models can be adapted to individual neural responses. We test this by asking whether frozen LLM representations encode person-specific EEG signals, directions in activation space that predict one person's brain activity but not another's. Using word-level EEG from 30 participants reading naturalistic sentences (ZuCo corpus), we train a separate linear probe for each person, mapping hidden states from a frozen Qwen 2.5 7B to that individual's EEG power. Person-specific probes outperform a single population probe on every EEG feature tested; for high-gamma power, the person-specific probe achieves rho = 0.183, a ninefold improvement over the population probe (rho = 0.020, p < 10^-4). A negative control, fixation count, shows no person-specific advantage (p = 0.360); fixation count reflects word length and frequency rather than individual cognition. The individual directions are temporally stable (split-half cosine = 0.824), non-transferable across people (self rho = 0.369 vs. other rho = 0.143, p < 10^-19), and distinct from the shared population signal: person-specific probes retain predictive power after the population component is removed. The person-specific signal concentrates in the model's deep layers, rising consistently with depth and peaking at Layer 24 of 28. The results are consistent across architectures (LLaMA 3.1 8B) and survive word-level confound controls. Frozen language models contain stable, person-specific neural directions in their deep layers, providing a geometric foundation for EEG-driven personalization.

翻译：消费级脑电图（EEG）正逐步进入日常设备（如耳塞、头带），这引发了语言模型能否适配个体神经响应的问题。我们通过探究冻结的LLM表征是否编码了特定个体的脑电图信号（即激活空间中能预测某一人脑活动但无法预测他人的方向）来验证这一点。基于30名被试阅读自然语句时的词级脑电数据（ZuCo语料库），我们为每个被试独立训练线性探针，将冻结的Qwen 2.5 7B模型的隐状态映射至该个体的脑电功率值。在所有测试的脑电特征上，个体特异性探针均优于单一群体探针：对于高伽马功率，个体特异性探针达到rho=0.183，较群体探针（rho=0.020, p<10^-4）提升九倍。阴性对照（注视次数）未表现出个体特异性优势（p=0.360），因为注视次数反映的是词长与词频而非个体认知差异。个体方向在时间上具有稳定性（分半余弦相似度=0.824），不可跨被试迁移（自身rho=0.369对比他人rho=0.143, p<10^-19），且与共享群体信号存在显著区别：移除群体成分后，个体特异性探针仍保持预测能力。个体特异性信号集中于模型深层，随深度递增，在第24层（共28层）达到峰值。该结果跨架构一致（LLaMA 3.1 8B），且通过词级混淆变量控制检验。冻结语言模型的深层中包含稳定、个体特异性的神经方向，为脑电驱动的个性化提供了几何基础。