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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gosh
    0.88
    ಗಾರ
    0.87
     Hace
    0.87
    님이
    0.86
    一看
    0.83
     principal
    0.79
    生
    0.79
     gerne
    0.78
     detour
    0.78
     कोई
    0.77
    POSITIVE LOGITS
    дық
    1.14
    ন
    1.07
    }(
    0.96
    nés
    0.96
    ians
    0.92
    emakers
    0.92
    ajjati
    0.91
    $}
    0.90
    ijiet
    0.89
    on
    0.89
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.