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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clare
    -0.07
     życ
    -0.07
     paraph
    -0.07
     harmed
    -0.07
    为什么不
    -0.07
    装饰
    -0.07
    大专
    -0.06
    עולם
    -0.06
    任何时候
    -0.06
     deviceId
    -0.06
    POSITIVE LOGITS
    _IA
    0.08
    _http
    0.08
    树立
    0.07
    /
↵
↵
    0.07
    Camera
    0.07
     guidelines
    0.07
     LTS
    0.07
    获
    0.07
    _CLIENT
    0.06
    íveis
    0.06
    Act Density 0.014%

    No Known Activations