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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    可想
    -0.07
    .Child
    -0.07
    (IService
    -0.06
     oczywiście
    -0.06
    _cmp
    -0.06
    焓
    -0.06
     kole
    -0.06
    �
    -0.06
     фон
    -0.06
    던
    -0.06
    POSITIVE LOGITS
    iação
    0.07
     билет
    0.07
    /#{
    0.07
    严重的
    0.07
    人次
    0.07
    _integral
    0.06
    Officers
    0.06
     ease
    0.06
    עו
    0.06
     batting
    0.06
    Act Density 0.000%

    No Known Activations