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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Despite
    0.89
     surpassing
    0.85
     данным
    0.80
     плохо
    0.79
     הספר
    0.79
    }),
    0.78
     plummet
    0.78
     может
    0.77
     Apesar
    0.77
     എന്നാല്‍
    0.75
    POSITIVE LOGITS
     arbres
    0.84
    ásra
    0.78
     feuilles
    0.77
     mattina
    0.73
    做
    0.72
     coût
    0.68
     cittadini
    0.68
     niñas
    0.68
     piedi
    0.68
    ječ
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.