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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    мо
    0.64
     so
    0.61
    на
    0.58
    ría
    0.57
    ম্প
    0.56
    itics
    0.56
     нет
    0.56
    嘍
    0.55
    so
    0.54
    喽
    0.53
    POSITIVE LOGITS
     ucz
    0.66
     Beyonce
    0.64
    Ahmed
    0.63
     Kanye
    0.62
     permitt
    0.61
     bahsed
    0.60
    Stadt
    0.60
     Lufthansa
    0.59
    有利
    0.58
     Kardash
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.