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

    Neuronpedia

    INDEX
    Explanations

    iz

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weights
    -0.07
    ёл
    -0.07
    (bounds
    -0.06
    ห
    -0.06
    avascript
    -0.06
    аного
    -0.06
     محمود
    -0.06
    .inflate
    -0.06
    .move
    -0.06
    _exp
    -0.06
    POSITIVE LOGITS
     climbing
    0.07
     geschichten
    0.07
    ichern
    0.07
     شهری
    0.07
     Religion
    0.06
    جاد
    0.06
    consumer
    0.06
     West
    0.06
    /request
    0.06
     анализ
    0.06
    Act Density 0.001%

    No Known Activations