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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    urul
    0.84
    il
    0.73
    ur
    0.71
    жи
    0.70
    坷
    0.70
    یرو
    0.68
     વિસ્ત
    0.67
    зу
    0.66
    stå
    0.66
    ির
    0.65
    POSITIVE LOGITS
    oriented
    0.86
    เฉพาะ
    0.81
    硖
    0.81
     abiert
    0.80
     opciones
    0.80
     oriented
    0.79
     cuarto
    0.77
     Allgemeinen
    0.77
     opcion
    0.77
     estadounidense
    0.76
    Act Density 0.001%

    No Known Activations