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

    Neuronpedia

    INDEX
    Explanations

    references to file errors and related programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    `src/` file paths and `ENUM` declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     let
    -0.33
     favor
    -0.32
     fled
    -0.31
    ➡
    -0.31
    ッジ
    -0.31
     pot
    -0.30
     consent
    -0.30
    lodash
    -0.29
    Cau
    -0.29
    LEGGI
    -0.29
    POSITIVE LOGITS
    脚注の使い方
    0.66
    tinyos
    0.65
     uLocal
    0.62
    ########.
    0.61
    findpost
    0.59
     nahilalakip
    0.59
     miniaturka
    0.57
    __(/*!
    0.56
    contentLoaded
    0.56
     kapturem
    0.56
    Act Density 0.191%

    No Known Activations