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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ח
    1.05
    स
    0.98
     ⿱
    0.84
    ל
    0.82
     compared
    0.82
    न
    0.82
    лин
    0.79
    на
    0.76
    ཿ
    0.75
    ווע
    0.73
    POSITIVE LOGITS
     zcela
    0.75
     altro
    0.74
    ca
    0.71
    ോളം
    0.71
     autre
    0.70
     notte
    0.70
     لازم
    0.70
     corrente
    0.70
     kese
    0.70
     jiné
    0.70
    Act Density 0.008%

    No Known Activations