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

    Neuronpedia

    INDEX
    Explanations

    return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]$,
    0.44
    istä
    0.44
    ,]
    0.42
     andRow
    0.42
    ]{
    0.42
    ]`
    0.41
    ‌است
    0.41
    *{
    0.40
     दरम्यान
    0.40
    )`,
    0.40
    POSITIVE LOGITS
    ش
    0.47
    ap
    0.46
    as
    0.46
    我
    0.46
     hilft
    0.42
    គ្រប់
    0.42
     Tecnología
    0.42
    Educ
    0.41
     könnte
    0.41
    Lis
    0.41
    Act Density 0.048%

    No Known Activations