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

    Neuronpedia

    INDEX
    Explanations

    org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     шир
    -0.08
    judge
    -0.07
    촛
    -0.07
    엶
    -0.07
    뱔
    -0.06
    ,’
    -0.06
    Fat
    -0.06
     ^
    -0.06
    𬣡
    -0.06
    ondere
    -0.06
    POSITIVE LOGITS
    .serializer
    0.09
    がか
    0.08
    _lstm
    0.08
     Datum
    0.08
     trò
    0.07
    演示
    0.07
     Maker
    0.07
     verschiedenen
    0.07
     Outputs
    0.07
     Joker
    0.07
    Act Density 0.001%

    No Known Activations