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

    Neuronpedia

    INDEX
    Explanations

    rating star honey signal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ılır
    0.79
    扛
    0.75
     IDs
    0.74
     $+$
    0.70
    ન્દ
    0.70
    ના
    0.70
     :#
    0.70
     progresses
    0.69
     》
    0.69
     IDA
    0.69
    POSITIVE LOGITS
     Вы
    0.83
    tní
    0.80
     ပြော
    0.75
     соревнования
    0.74
     কোন
    0.72
     снима
    0.72
     mamá
    0.72
     bạn
    0.71
     игры
    0.71
    සුව
    0.71
    Act Density 0.001%

    No Known Activations