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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ś
    0.84
    ниця
    0.79
     guts
    0.78
     assegn
    0.75
     nicely
    0.75
    接
    0.73
     acc
    0.73
    f
    0.70
     discerned
    0.69
     processed
    0.69
    POSITIVE LOGITS
     dire
    1.05
    Dire
    0.97
    onError
    0.90
    ListIterator
    0.87
    onclick
    0.83
    ciri
    0.82
    cdots
    0.81
    dirs
    0.80
    talet
    0.79
    siz
    0.77
    Act Density 0.000%

    No Known Activations