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

    Neuronpedia

    INDEX
    Explanations

    <|

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    coded
    -0.08
    .Decode
    -0.08
    .GetAxis
    -0.07
    ѫ
    -0.07
    水电
    -0.07
     stochastic
    -0.07
    无法
    -0.07
    套餐
    -0.07
     hoje
    -0.07
    ofday
    -0.07
    POSITIVE LOGITS
    '\
    0.08
     ideal
    0.07
    _BINDING
    0.07
    被认为是
    0.07
     Offering
    0.07
     QUESTION
    0.07
    ORK
    0.07
     planting
    0.07
     bearing
    0.06
    ger
    0.06
    Act Density 0.001%

    No Known Activations