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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    gi
    0.82
    ya
    0.78
    e
    0.76
    y
    0.75
    el
    0.72
    t
    0.72
     podrá
    0.71
    g
    0.71
     permitir
    0.70
    yd
    0.70
    POSITIVE LOGITS
    いましたが
    0.92
    сей
    0.86
    Б
    0.86
    нең
    0.79
     millilit
    0.77
     camere
    0.77
    買った
    0.77
    рои
    0.76
    িয়ার
    0.75
    أ
    0.74
    Act Density 0.001%

    No Known Activations