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

    Neuronpedia

    INDEX
    Explanations

    dogs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Payments
    -0.07
    atisch
    -0.07
     ctor
    -0.07
    _PM
    -0.07
    tgt
    -0.07
    SupportedContent
    -0.06
     göre
    -0.06
    סר
    -0.06
    运算
    -0.06
    وط
    -0.06
    POSITIVE LOGITS
     Lik
    0.08
    ﹗
    0.07
    בנייה
    0.07
    �
    0.07
     течение
    0.06
    (mock
    0.06
    可以让
    0.06
    �
    0.06
    加工厂
    0.06
    Lang
    0.06
    Act Density 0.001%

    No Known Activations