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

    Neuronpedia

    INDEX
    Explanations

    elements related to the syntax and structure of programming variables

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

    Mathematical symbols and special characters

    np_acts-logits-general · gemini-2.0-flash

    special characters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.82
     typelib
    -0.73
     ""))
    -0.71
     المعيارى
    -0.68
    ."]
    -0.67
    NUMX
    -0.66
    BeginContext
    -0.66
    '')
    -0.65
     ""));
    -0.65
    脚注の使い方
    -0.64
    POSITIVE LOGITS
     symbol
    1.10
     symbols
    1.02
     Symbols
    0.89
     symboles
    0.88
     symbole
    0.87
     marks
    0.86
    Symbol
    0.85
     Symbol
    0.85
    symbol
    0.85
     signs
    0.84
    Act Density 0.884%

    No Known Activations