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

    Neuronpedia

    INDEX
    Explanations

    words ending in am, em, or cham

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    1.65
    p
    1.35
    de
    1.18
    /
    1.13
    a
    1.10
     Reverso
    1.08
    ాలు
    1.05
    an
    1.04
    د
    1.02
    你
    1.02
    POSITIVE LOGITS
    ม
    1.57
    ми
    1.38
     on
    1.38
    人
    1.36
    트
    1.28
    পত্র
    1.24
     as
    1.22
    ند
    1.22
    った
    1.20
     in
    1.18
    Act Density 0.275%

    No Known Activations