尼尔·南达 Neel NandaNeel Nanda
Google DeepMind
Google DeepMind 机制可解释性负责人Mechanistic Interpretability Lead, Google DeepMind
safety
领导 Google DeepMind 的机制可解释性团队。在「理解大模型内部」上影响广泛,以公开教程、TransformerLens 库与叠加(superposition)研究著称。
Leads the mechanistic interpretability team at Google DeepMind. A prominent educator on understanding the internals of language models, known for open tutorials, the TransformerLens library and superposition research.
在关系图谱中查看 尼尔·南达 →View Neel Nanda in the graph →