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

    Neuronpedia

    INDEX
    Explanations

    lottery and jackpot numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fonctionnal
    0.50
    涹
    0.45
    न्दावन
    0.44
    罾
    0.42
     theres
    0.40
     macroph
    0.40
     lipids
    0.40
     frescoes
    0.40
     acide
    0.39
    ំនួន
    0.39
    POSITIVE LOGITS
    .
    0.42
     refers
    0.42
    block
    0.41
    wise
    0.40
    x
    0.40
    com
    0.39
    是一家
    0.39
    common
    0.39
    ma
    0.38
    air
    0.38
    Act Density 0.000%

    No Known Activations