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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    otherapy
    0.75
     noires
    0.74
     Tuhan
    0.74
     година
    0.72
     médical
    0.71
    وضع
    0.71
     noirs
    0.70
    ऐसा
    0.69
    axie
    0.69
    今回
    0.68
    POSITIVE LOGITS
    서는
    1.01
    นาน
    0.76
    зы
    0.73
    lara
    0.73
     эн
    0.72
    residual
    0.71
    en
    0.71
    erd
    0.70
    lere
    0.70
    서를
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.