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

    Neuronpedia

    INDEX
    Explanations

    programming terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TRPV
    0.77
     ﺍﻟ
    0.75
     ましょう
    0.73
     PFAS
    0.73
    zovaniyu
    0.70
     ພວກເຮົາ
    0.70
    ၷ
    0.68
     dystopian
    0.68
    𝗥
    0.68
    CTOGRAM
    0.67
    POSITIVE LOGITS
    new
    0.69
    data
    0.64
    test
    0.64
    print
    0.64
    name
    0.63
    public
    0.63
    index
    0.61
    this
    0.61
    temp
    0.61
    return
    0.60
    Act Density 2.300%

    No Known Activations