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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ค่ะ
    -0.85
    ambiguous
    -0.85
    uyện
    -0.82
    titutions
    -0.81
    IModel
    -0.81
     אנשים
    -0.80
     bonos
    -0.79
     кожа
    -0.79
     suites
    -0.79
     आइटम
    -0.77
    POSITIVE LOGITS
    ꯊ
    0.84
     ENGINEER
    0.82
     Ensuring
    0.82
    featuring
    0.79
     کمک
    0.78
     vérifier
    0.78
    arlo
    0.77
    número
    0.77
    acı
    0.77
    jenner
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.