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

    Neuronpedia

    INDEX
    Explanations

    logging, GCC, regions, libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entourage
    0.73
    larında
    0.70
    zinho
    0.66
     кеңсе
    0.62
    势力
    0.57
     মনের
    0.57
    🈶
    0.57
    lerinde
    0.57
     adhik
    0.56
    bler
    0.55
    POSITIVE LOGITS
     уви
    0.87
    ти
    0.82
    น
    0.79
    ה
    0.71
    the
    0.70
    ه
    0.66
    њ
    0.66
    ко
    0.66
    ق
    0.65
    ้ำ
    0.65
    Act Density 0.000%

    No Known Activations