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

    Neuronpedia

    INDEX
    Explanations

    specific keywords and following tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.52
    5
    0.47
    Chia
    0.46
    4
    0.45
    ги
    0.45
    Units
    0.44
    пи
    0.44
    奪
    0.44
    優
    0.43
    地理
    0.41
    POSITIVE LOGITS
     ሌሎች
    0.46
    honneur
    0.45
     파일
    0.45
     getchar
    0.44
    ustral
    0.44
    wali
    0.44
    èque
    0.44
    står
    0.43
     ገን
    0.42
    ystycz
    0.42
    Act Density 0.001%

    No Known Activations