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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cuando
    0.82
    ০
    0.82
     erhält
    0.80
    ှ
    0.80
    ଐ
    0.79
     direkt
    0.77
     når
    0.77
    produkt
    0.77
     phép
    0.77
    まれ
    0.77
    POSITIVE LOGITS
    ન્મ
    0.71
    ર
    0.70
     uncertainty
    0.68
     Тем
    0.67
     важ
    0.65
     особли
    0.64
     Сла
    0.63
     المض
    0.63
     Ora
    0.63
    oretum
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.