大模型的大脑，也分区干活
人脑不是一块均质的肉，它有专门管语言、管逻辑、管社交、管物理直觉的片区。这篇论文发现，大模型内部也长出了类似的分区：让模型做46种任务，凡是人类大脑用同一片区处理的，模型里激活的也是同一批神经元；人类大脑用不同片区的，模型里也是不同批。两个完全不同的系统，却收敛出同一种组织方式——这暗示模块化可能是智能的底层规律，而不是生物进化的偶然。它不是你明天能用上的东西，但如果你关心“AI到底像不像人”，这是目前最硬核的证据之一。
📄 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.