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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and function definitions in code

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

    class declarations and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.74
     defaultstate
    -0.69
    Identyfik
    -0.54
    DoubleQuotes
    -0.53
     <=",
    -0.50
    +#+#
    -0.49
    :✨
    -0.49
     समीक्षाएं
    -0.46
    DockStyle
    -0.45
     صوتيه
    -0.45
    POSITIVE LOGITS
    tgz
    0.54
     évêque
    0.47
     виправивши
    0.42
    seigneur
    0.41
     lecteur
    0.41
    szönöm
    0.39
    mobileqq
    0.38
    yship
    0.38
     ouvriers
    0.37
     lecteurs
    0.37
    Act Density 0.088%

    No Known Activations