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

    Neuronpedia

    INDEX
    Explanations

    Let's have some

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    萸
    0.77
     পাওয়া
    0.73
    นะคะ
    0.73
     ద్వారా
    0.72
    有一些
    0.71
     adlı
    0.71
     związ
    0.69
    }},
    0.68
     goes
    0.68
     ورحمه
    0.68
    POSITIVE LOGITS
    第一題
    0.79
    新たな
    0.76
    fishing
    0.73
     একটা
    0.71
    ycled
    0.70
    cycled
    0.70
     spectrometry
    0.68
    beliefs
    0.68
    thin
    0.68
    électricité
    0.67
    Act Density 0.058%

    No Known Activations