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

    Neuronpedia

    INDEX
    Explanations

    `ARG`, `Unit`, `cfg`, `core`, `local`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     były
    0.64
     tecnológico
    0.63
    WhiteRatingDiff
    0.61
     hidrógeno
    0.59
     četiri
    0.59
    İN
    0.57
     pulgadas
    0.57
     séptimo
    0.57
     seleccionado
    0.57
     cinética
    0.56
    POSITIVE LOGITS
    整
    0.51
    อัน
    0.47
    s
    0.47
    0.45
    少
    0.45
     as
    0.45
    nm
    0.44
    (
    0.42
    0
    0.41
    快
    0.40
    Act Density 0.001%

    No Known Activations