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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ak
    0.93
    を果た
    0.82
    اعر
    0.81
    au
    0.80
    awasan
    0.79
     Conselho
    0.79
     aneu
    0.79
     bew
    0.79
     fino
    0.79
    ah
    0.78
    POSITIVE LOGITS
    入门
    0.73
     भवि
    0.73
    一开始
    0.73
    ปล่อย
    0.68
    utig
    0.67
     emisión
    0.67
    户
    0.66
    这么
    0.64
    ム
    0.64
    нің
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.