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

    Neuronpedia

    INDEX
    Explanations

    technical abbreviations and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     üçün
    0.48
     üzerinden
    0.42
     cầu
    0.42
    я
    0.42
     înce
    0.41
    ີ້
    0.40
     обновление
    0.40
     баста
    0.40
    িগ্ন
    0.39
    电源
    0.39
    POSITIVE LOGITS
    Pan
    0.45
    Trem
    0.44
    Br
    0.44
    epart
    0.43
    Comp
    0.43
    Bl
    0.42
    Depart
    0.42
     Dis
    0.41
     Tit
    0.41
    Sic
    0.41
    Act Density 0.002%

    No Known Activations