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

    Neuronpedia

    INDEX
    Explanations

    constraint

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Alpha
    -0.07
    ."},↵
    -0.07
    趣
    -0.07
    (
    -0.07
    玑
    -0.06
     pockets
    -0.06
     bổ
    -0.06
    -Allow
    -0.06
     Autumn
    -0.06
    _plot
    -0.06
    POSITIVE LOGITS
    rame
    0.07
     congressman
    0.07
    removeAttr
    0.07
    userName
    0.07
    压力
    0.07
     STDMETHOD
    0.06
     CONSTANT
    0.06
     brewery
    0.06
     Congressman
    0.06
    コン
    0.06
    Act Density 0.009%

    No Known Activations