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

    Neuronpedia

    INDEX
    Explanations

    syntax elements related to code imports and variable declarations

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

    html tags and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.61
    FunctionFlags
    -0.56
     invokingState
    -0.55
    tangentMode
    -0.53
    getRuntime
    -0.50
     pinulongan
    -0.49
    addCriterion
    -0.48
    AndEndTag
    -0.48
    DrawerToggle
    -0.48
    VPWR
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.63
    complexContent
    0.43
    SuspendLayout
    0.41
     internetowa
    0.40
    +#+#
    0.35
     boats
    0.35
    ouncements
    0.35
    guous
    0.35
    дей
    0.35
     myſelf
    0.34
    Act Density 0.000%

    No Known Activations