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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    al
    0.80
    ฝ่าย
    0.77
    n
    0.77
     legislación
    0.76
    l
    0.75
    라고
    0.73
     отказыва
    0.72
     বে
    0.71
    quele
    0.71
    ra
    0.71
    POSITIVE LOGITS
     maximizes
    0.71
     maximize
    0.69
    PATH
    0.68
    сну
    0.67
    嵘
    0.67
    偣
    0.66
    利き
    0.65
     собі
    0.64
    ၸ
    0.64
    бере
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.