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

    Neuronpedia

    INDEX
    Explanations

    key explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     최대한
    0.88
     המו
    0.80
     מו
    0.79
     మరింత
    0.77
     Уни
    0.73
    一身
    0.73
     Loan
    0.72
     End
    0.72
     кін
    0.72
     కా
    0.71
    POSITIVE LOGITS
    TL
    0.94
     Beverly
    0.70
    Trades
    0.69
     disturbing
    0.68
    Washington
    0.67
     खड़े
    0.67
     habitable
    0.66
     quận
    0.66
     Sarasota
    0.65
    ltal
    0.64
    Act Density 0.011%

    No Known Activations