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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    دى
    0.84
    潵
    0.78
     Tayyip
    0.77
    atasaray
    0.73
    $)$.
    0.73
     पर्सन
    0.72
     spirituality
    0.71
     %).
    0.71
    ಾರೆ
    0.70
    ت
    0.70
    POSITIVE LOGITS
     ds
    0.75
     لاز
    0.72
    ox
    0.71
    mejor
    0.71
     wx
    0.71
     dieser
    0.70
    ut
    0.69
     for
    0.69
    omorphism
    0.68
    Adapt
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.