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

    Neuronpedia

    INDEX
    Explanations

    documentation comments, parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    בּ
    0.37
    erra
    0.37
    Berk
    0.35
    Wert
    0.35
    Raquete
    0.35
    پوینت
    0.34
    روج
    0.34
    שׁ
    0.34
    ាស់
    0.33
     }+\
    0.33
    POSITIVE LOGITS
    param
    1.02
     param
    0.98
     @
    0.79
     Param
    0.73
    Args
    0.71
    PARAM
    0.68
     PARAM
    0.67
     Args
    0.65
    Param
    0.62
    参数
    0.62
    Act Density 0.034%

    No Known Activations