Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    OpenAI URL paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    仿佛
    0.45
    levelname
    0.40
     Stanley
    0.39
    ፔ
    0.39
     upland
    0.39
    Stanley
    0.39
     ident
    0.38
     alpine
    0.38
    ﻖ
    0.37
     stage
    0.37
    POSITIVE LOGITS
     OpenAI
    0.56
     GPT
    0.55
    openai
    0.53
    GPT
    0.52
     API
    0.51
     openai
    0.51
    gpt
    0.48
     APIs
    0.44
    接口
    0.44
    aleb
    0.39
    Act Density 0.017%

    No Known Activations