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

    Neuronpedia

    INDEX
    Explanations

    digits starting with 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াইয়৷
    0.50
     Elytres
    0.47
    的处理
    0.47
     организм
    0.47
    ContextHeader
    0.46
    ১২শ
    0.46
    EnglishMarks
    0.46
    BackgroundHelper
    0.46
     दट
    0.45
     NumericVector
    0.45
    POSITIVE LOGITS
    t
    0.67
    k
    0.66
    et
    0.63
    m
    0.63
     A
    0.59
    z
    0.59
    p
    0.58
    x
    0.58
    g
    0.56
    f
    0.56
    Act Density 0.142%

    No Known Activations