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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ры
    1.03
     было
    0.86
     которые
    0.83
    жным
    0.82
    дной
    0.82
     общей
    0.81
    рые
    0.80
     оказалось
    0.80
    рный
    0.80
    ถึง
    0.79
    POSITIVE LOGITS
     intervalles
    0.77
    ifiés
    0.71
     offrire
    0.71
    Bola
    0.70
     nostra
    0.68
     leggi
    0.68
     progressivement
    0.66
     auctor
    0.66
     tradu
    0.66
     vitesses
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.