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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     hice
    1.02
    ッテリー
    0.81
     oversaw
    0.77
     injective
    0.77
     adorned
    0.77
     aucun
    0.75
    ضمن
    0.75
     menos
    0.75
     viv
    0.75
     incluye
    0.74
    POSITIVE LOGITS
     Janata
    0.84
    만
    0.80
    กฏ
    0.79
    ర
    0.78
    Mathematics
    0.77
    Ту
    0.75
    多様
    0.74
    Obj
    0.74
    臺灣
    0.73
    SUN
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.