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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     champion
    0.89
    的一个
    0.87
     tangent
    0.86
     Saxon
    0.86
     βρίσκεται
    0.86
     Barbados
    0.85
     Château
    0.85
    Saxon
    0.84
    テゴ
    0.84
    此之外
    0.84
    POSITIVE LOGITS
    ﻮ
    0.95
    ного
    0.90
    ных
    0.90
     вопро
    0.88
    ovať
    0.84
    НЫ
    0.82
    ной
    0.81
    ^{*}$-
    0.80
    ﺪ
    0.80
     ि
    0.79
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.