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

    Neuronpedia

    INDEX
    Explanations

    constructor parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     redshift
    0.82
     KeyError
    0.73
     redshifts
    0.66
     semicolon
    0.64
     bhfu
    0.63
     checksum
    0.63
    컫
    0.62
     vouchers
    0.61
     dàng
    0.61
     aceste
    0.60
    POSITIVE LOGITS
     उसमें
    0.56
    Enumer
    0.54
     housewife
    0.53
    รา
    0.51
    But
    0.50
    utusan
    0.49
    Projeto
    0.47
    ម
    0.47
    tie
    0.46
    밀
    0.46
    Act Density 0.001%

    No Known Activations