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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    wegen
    0.73
    ي
    0.73
    Weekday
    0.71
     ")");
    0.68
    art
    0.68
     организация
    0.67
    ת
    0.67
    ari
    0.66
    achen
    0.63
    Below
    0.63
    POSITIVE LOGITS
     democracies
    0.89
     DNN
    0.84
    ﻨ
    0.84
     PTFE
    0.82
     positron
    0.79
    ﺮ
    0.79
     এছাড়াও
    0.78
     vidro
    0.76
     jì
    0.76
     emuls
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.