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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Από
    0.67
     CtApp
    0.62
     xảy
    0.62
     sempat
    0.62
    weza
    0.60
    Campaign
    0.60
     pandemi
    0.60
    inquirer
    0.59
     onPress
    0.59
    #%%
    0.59
    POSITIVE LOGITS
    ます
    0.86
    i
    0.79
    とっても
    0.78
    ますが
    0.78
    ে
    0.71
    remely
    0.68
    dbi
    0.68
     vrlo
    0.67
     einfache
    0.67
     primul
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.