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

    Neuronpedia

    INDEX
    Explanations

    converting to int

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    piej
    0.49
     lastname
    0.46
     சிலையின்
    0.46
     Jungkook
    0.45
    竰
    0.45
     می‌کند
    0.45
     περίπτωση
    0.45
     Mitarbeiter
    0.44
    extrémité
    0.44
     смерть
    0.44
    POSITIVE LOGITS
    in
    0.84
    int
    0.67
    for
    0.65
    c
    0.64
    that
    0.62
    p
    0.59
    ק
    0.59
    ov
    0.57
     that
    0.57
     as
    0.57
    Act Density 0.003%

    No Known Activations