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

    Neuronpedia

    INDEX
    Explanations

    the presence of open parentheses or similar characters

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

    function parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeText
    -0.64
    tagHelperRunner
    -0.58
    httphttps
    -0.56
     ویکی‌پدیا
    -0.50
    DeleteBehavior
    -0.49
     nemlig
    -0.49
     vielmehr
    -0.48
    addCriterion
    -0.48
    Välislingid
    -0.47
     Италијани
    -0.47
    POSITIVE LOGITS
     astore
    0.50
    (
    0.43
     (
    0.40
    selectBy
    0.39
    Gam
    0.36
    랍
    0.36
    :^(
    0.36
    hiko
    0.35
    ibouti
    0.35
     walker
    0.35
    Act Density 0.021%

    No Known Activations