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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    м
    1.06
    يند
    0.92
     seta
    0.89
    ब्र
    0.80
    ﻣ
    0.79
    ا
    0.78
    બ
    0.78
    وني
    0.77
    ី
    0.73
    ًا
    0.73
    POSITIVE LOGITS
     restricciones
    0.73
     pequeños
    0.71
    Serialized
    0.69
    CIÓN
    0.69
    iro
    0.68
    Token
    0.66
    কারীর
    0.66
     añad
    0.64
     vaya
    0.64
     personalizar
    0.64
    Act Density 0.001%

    No Known Activations