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

    Neuronpedia

    INDEX
    Explanations

    Protocol buffers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    细胞
    -0.08
    lets
    -0.07
    react
    -0.07
     scatter
    -0.07
    溵
    -0.07
    营运
    -0.07
    槍
    -0.06
    _scene
    -0.06
    쟤
    -0.06
    yet
    -0.06
    POSITIVE LOGITS
    匡
    0.08
    コーヒ
    0.07
     eas
    0.07
    究
    0.07
     SR
    0.07
    vais
    0.07
     обязатель
    0.07
    Walker
    0.07
     improvements
    0.07
    AK
    0.07
    Act Density 0.000%

    No Known Activations