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

    Neuronpedia

    INDEX
    Explanations

    defining modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attendant
    0.38
     NODE
    0.37
     эк
    0.36
     rispetto
    0.36
     artisan
    0.36
     wept
    0.36
     Nam
    0.35
     двух
    0.35
    确定
    0.35
    ㄿ
    0.35
    POSITIVE LOGITS
    ボ
    0.41
    িয়ন
    0.38
     '),
    0.38
     páginas
    0.36
    ಾಗಿತ್ತು
    0.35
     {'
    0.35
    ),"
    0.35
    貘
    0.35
     ',
    0.35
    decimal
    0.34
    Act Density 0.000%

    No Known Activations