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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     de
    0.50
    /*
    0.45
     over
    0.44
     spectators
    0.43
    lets
    0.41
     salvo
    0.41
     be
    0.41
     બાદ
    0.40
     officials
    0.40
    vang
    0.40
    POSITIVE LOGITS
     เลือก
    0.57
     रोगों
    0.55
     цену
    0.54
     Describes
    0.50
     វា
    0.50
     〢
    0.49
     функции
    0.49
    စျေး
    0.49
     заболеваний
    0.48
     şeyi
    0.48
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.