AI 大脑也分区：大模型内部竟长出了类似人脑的模块
人脑不是一块均质的肉，它有专门管语言、管逻辑、管社交、管物理世界的分区。研究者发现，大模型内部也长出了类似的分区：让模型做语言任务时，激活的神经元和做社交推理时激活的神经元几乎不重叠，就像人脑的语言区和社交区各干各的。这种结构不是人设计的，而是模型自己训练出来的。它说明，智能系统可能天生就需要这种模块化分工——这或许能帮我们理解 AI 为什么会犯某些错误，以及如何让 AI 更可靠。但这不是你明天就能用上的功能，它更像是在告诉我们：AI 的“大脑”比我们以为的更像人脑。
📄 原文摘要(英文)
The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world. Is this modular organization a fundamental principle of how intelligent systems must be built, or an evolutionary accident specific to biological brains? Here, we test whether a similar organization emerges in Large Language Models--another class of intelligent systems created through a very different optimization process. Using circuit analyses across N=46 tasks spanning four cognitive domains (language, formal reasoning, social reasoning, physical reasoning), we find that LLMs develop a modular architecture that mirrors the human brain: tasks drawing on the same network in humans recruit overlapping neurons in LLMs, whereas tasks drawing on different networks recruit distinct neurons. The convergent emergence of modularity in brains and neural networks suggests that it may be a fundamental property of intelligent systems.