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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    あら
    0.52
    ﺇ
    0.50
    StartsWith
    0.49
    ので
    0.48
    administrator
    0.48
     ہدایت
    0.47
    テーブル
    0.46
    Noun
    0.45
     ADMINISTRATION
    0.45
    ALIAS
    0.44
    POSITIVE LOGITS
    }}}}$
    0.45
     slopes
    0.44
     Dorm
    0.43
     quiescent
    0.42
     wipers
    0.42
     xScale
    0.42
    ógio
    0.41
     Rap
    0.41
     Falling
    0.41
     discontinuities
    0.40
    Act Density 0.002%

    No Known Activations