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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     totam
    0.72
     importance
    0.70
     nincs
    0.69
     Bookstore
    0.67
     Absence
    0.66
     muque
    0.64
    ไม่มี
    0.64
     Pentru
    0.63
    indazol
    0.63
     немає
    0.62
    POSITIVE LOGITS
    ى
    0.79
    ように
    0.77
    тров
    0.77
    zd
    0.74
    offer
    0.74
    ногие
    0.73
     fudai
    0.72
    幕
    0.71
    hende
    0.71
    вица
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.