Fewer Than 0.1% of Neurons Predict When LLMs Hallucinate2026-02-25T00:00:00Z•11 min read#mechanistic-interpretability#hallucination#llm-internals#neurons#alignmentFewer than one in a thousand neurons in a large language model can predict whether it's about to hallucinate -- and they encode something unexpected: not factual errors, but a tendency toward compliance over truth.