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

    Neuronpedia

    INDEX
    Explanations

    note after connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     angular
    0.41
     muscular
    0.39
     pooled
    0.38
     fi
    0.38
     lit
    0.38
     alters
    0.38
     prett
    0.38
     originality
    0.37
     granularity
    0.37
     architectural
    0.37
    POSITIVE LOGITS
    धिकारियों
    0.41
    isele
    0.40
     Только
    0.39
     Спасибо
    0.38
     Благодаря
    0.38
    ऐसा
    0.37
     обязан
    0.37
    Only
    0.37
    ього
    0.36
     Многие
    0.36
    Act Density 0.001%

    No Known Activations