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

    Neuronpedia

    INDEX
    Explanations

    foreign language elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.39
     of
    0.36
     to
    0.35
     Cultures
    0.34
     Approx
    0.34
     but
    0.33
     Total
    0.32
     and
    0.32
    to
    0.32
     Those
    0.32
    POSITIVE LOGITS
     спорттук
    0.35
    <0x1D>
    0.35
     మీరు
    0.35
    дзен
    0.35
     sélectionnez
    0.35
    жмите
    0.35
     середине
    0.34
    ሖ
    0.34
     bạn
    0.34
     seleccione
    0.34
    Act Density 0.000%

    No Known Activations