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

    Neuronpedia

    INDEX
    Explanations

    text relating to transformations and dividing something up

    oai_token-act-pair · gemini-2.0-flash

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     into
    -0.56
     rowspan
    -0.56
    َه
    -0.55
     Abonnez
    -0.53
    Into
    -0.52
    into
    -0.50
    bbene
    -0.49
     Into
    -0.48
    alde
    -0.47
     thành
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.75
    Personensuche
    0.71
    MigrationBuilder
    0.71
     ویکی‌پدی
    0.66
     للاسماء
    0.63
    NameInMap
    0.60
    تقاوى
    0.60
     actionMode
    0.59
     المرجع
    0.57
    !*\
    0.56
    Act Density 6.790%

    No Known Activations