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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and functions

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

    function with index argument

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorTagHelper
    -0.58
    msgTypes
    -0.54
    oredCriteria
    -0.52
    PerformLayout
    -0.52
     nahilalakip
    -0.50
     EconPapers
    -0.48
    ⅘
    -0.45
    zeuge
    -0.43
    RuleContext
    -0.43
     архивлан
    -0.42
    POSITIVE LOGITS
    Pocket
    0.37
     pocket
    0.37
     Pocket
    0.36
    ustra
    0.35
     tiefen
    0.35
    انجليز
    0.34
     Derechos
    0.34
    imab
    0.34
     Gespräche
    0.34
     Geschmack
    0.33
    Act Density 0.261%

    No Known Activations