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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Familie
    0.51
     Childhood
    0.46
    全民
    0.46
     Lebens
    0.46
     フル
    0.46
    アマ
    0.46
     चैलेंज
    0.46
    द्धांत
    0.45
    謾
    0.44
    暊
    0.44
    POSITIVE LOGITS
    나
    0.45
    istic
    0.43
    all
    0.42
    le
    0.40
    MLLoader
    0.40
    a
    0.39
    MQ
    0.39
    _{
    0.38
     hovered
    0.38
     alerts
    0.37
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.