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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Ее
    0.81
    k
    0.80
    d
    0.78
     odometer
    0.75
    m
    0.75
     ballast
    0.73
     Gestión
    0.73
    g
    0.73
    צ
    0.73
    pubescens
    0.71
    POSITIVE LOGITS
     Produkten
    0.80
    ডির
    0.74
     Ajouter
    0.74
    以外
    0.72
     terus
    0.71
    瓏
    0.71
    Supported
    0.69
    таки
    0.69
     ramai
    0.67
    خدام
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.