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

    Neuronpedia

    INDEX
    Explanations

    after specified word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    byId
    0.42
    num
    0.41
    }@
    0.40
    batis
    0.39
     tru
    0.38
    >((
    0.38
     p
    0.38
    OrFail
    0.38
    மாவ
    0.37
    データを
    0.37
    POSITIVE LOGITS
    竞争
    0.45
    競争
    0.41
    ushchev
    0.41
    ֖
    0.41
     enseñanza
    0.41
     Specific
    0.40
     instalado
    0.39
     voluntad
    0.39
     específica
    0.39
     Specified
    0.39
    Act Density 0.000%

    No Known Activations