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

    Neuronpedia

    INDEX
    Explanations

    colors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (“
    -0.07
    眼光
    -0.07
    给出
    -0.07
     Town
    -0.07
    amide
    -0.07
    _create
    -0.07
    𝕎
    -0.07
    fillable
    -0.07
     Colors
    -0.07
    盘活
    -0.06
    POSITIVE LOGITS
    峧
    0.07
     Password
    0.07
    sexo
    0.06
     призна
    0.06
     happens
    0.06
     analys
    0.06
     ironic
    0.06
     serial
    0.06
    =[↵
    0.06
    基石
    0.06
    Act Density 0.038%

    No Known Activations