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

    Neuronpedia

    INDEX
    Explanations

    random numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     활용
    0.72
     ছেলেরা
    0.70
     rivers
    0.70
     boys
    0.69
    asco
    0.69
    MLLoader
    0.67
    اکی
    0.66
    स्ता
    0.65
     Younger
    0.65
    溦
    0.64
    POSITIVE LOGITS
    парат
    0.79
    ข้อมูล
    0.78
     information
    0.73
     informieren
    0.71
    leton
    0.70
    information
    0.68
    สนใจ
    0.68
     trochę
    0.67
    Variables
    0.65
    Station
    0.65
    Act Density 0.001%

    No Known Activations