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

    Neuronpedia

    INDEX
    Explanations

    elements of programming language syntax, particularly related to code structure

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

    code and multilingual terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.71
    UserScript
    -0.67
    aarrggbb
    -0.62
    uxxxx
    -0.59
     Commen
    -0.59
     zwiſchen
    -0.57
    ."],
    -0.57
    postIndex
    -0.56
    ஫
    -0.56
     verſch
    -0.55
    POSITIVE LOGITS
     soorten
    0.38
     república
    0.35
     Katze
    0.35
     Nutzungs
    0.34
     szint
    0.34
    retudo
    0.33
     Erkenntnis
    0.31
    śred
    0.31
     viszont
    0.31
     keuken
    0.30
    Act Density 0.001%

    No Known Activations