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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    因子
    0.48
     cosi
    0.43
     नाश
    0.41
     television
    0.41
     तथ
    0.41
     ഇങ്ങനെ
    0.40
     fragrant
    0.40
     puncture
    0.39
     televisions
    0.39
     actin
    0.39
    POSITIVE LOGITS
    as
    0.49
    给
    0.45
    ir
    0.43
    gives
    0.42
    gu
    0.41
    rich
    0.41
    用于
    0.40
    null
    0.40
    gir
    0.40
    has
    0.39
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.