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

    Neuronpedia

    INDEX
    Explanations

    structure or formatting elements in code snippets

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

    Code snippets or errors followed by "print"

    np_acts-logits-general · gemini-2.0-flash

    printing code statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wpdb
    -0.62
    المراجع
    -0.56
    PathVariable
    -0.55
    مراجع
    -0.55
    Permalink
    -0.55
     textStatus
    -0.55
     Auss
    -0.54
     strconv
    -0.54
    SuspendLayout
    -0.54
    EntityFramework
    -0.53
    POSITIVE LOGITS
     للاسماء
    0.90
    <unused63>
    0.78
    uxxxx
    0.75
    <unused62>
    0.72
    /*
    0.68
    <unused61>
    0.68
     متعلقه
    0.67
    <unused60>
    0.65
     becauſe
    0.64
     fufficient
    0.64
    Act Density 0.138%

    No Known Activations