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

    Neuronpedia

    INDEX
    Explanations

    world class, world of, world-building

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مي
    1.51
    ك
    1.36
    on
    1.34
    مو
    1.27
    л
    1.23
     мог
    1.21
    ح
    1.20
    ai
    1.19
    وك
    1.18
    ايا
    1.18
    POSITIVE LOGITS
    0
    1.30
    <0x80>
    1.30
     the
    1.15
    \
    1.12
    (
    1.09
    h
    1.06
    ۰
    1.05
    the
    1.03
     innovative
    1.03
    )
    1.02
    Act Density 0.054%

    No Known Activations