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

    Neuronpedia

    INDEX
    Explanations

    instances of indentation or structured formatting in code snippets

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

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.82
    bootstrapcdn
    -0.76
    elemField
    -0.75
     Италијани
    -0.75
     newOwner
    -0.66
    msgTypes
    -0.66
    -0.66
    reportWebVitals
    -0.65
     ویکی‌آمباردا
    -0.65
    yarnpkg
    -0.64
    POSITIVE LOGITS
     
    0.43
    <?
    0.43
     recent
    0.42
     Tail
    0.35
     tail
    0.35
    Recent
    0.34
    Trailing
    0.34
     reciente
    0.33
     Trail
    0.33
    SuspendLayout
    0.33
    Act Density 0.001%

    No Known Activations