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

    Neuronpedia

    INDEX
    Explanations

    integer limits and goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     హీరోయి
    0.47
    𝓌
    0.42
    繩
    0.41
    barplot
    0.41
    decre
    0.40
     actresses
    0.40
    aš
    0.38
    前辈
    0.38
     নায়িকা
    0.38
    ﻄ
    0.37
    POSITIVE LOGITS
     illicit
    0.40
    PSC
    0.40
     عمد
    0.39
    [[
    0.38
    экс
    0.38
     coloc
    0.37
     excessive
    0.37
    Opts
    0.37
     там
    0.36
     Mag
    0.35
    Act Density 0.001%

    No Known Activations