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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Scaler
    0.44
    GradientPanel
    0.43
     partea
    0.41
     聞い
    0.41
    യി
    0.41
    dataReader
    0.41
    saldo
    0.41
    頜
    0.41
    КП
    0.40
    ⿰
    0.40
    POSITIVE LOGITS
    原
    0.42
     Allow
    0.41
    χ
    0.41
     Defined
    0.40
             
    0.39
     May
    0.39
    час
    0.38
    怯
    0.38
    al
    0.38
     June
    0.37
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.