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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the '#' symbol, indicating preprocessor directives or comments in code

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

    C/C++ preprocessor directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HideFlags
    -0.72
    AutoModerator
    -0.68
    InjectAttribute
    -0.67
    KURZBESCHREIBUNG
    -0.61
     >=",
    -0.61
     betweenstory
    -0.59
     IFTT
    -0.59
     propOrder
    -0.57
     ModelExpression
    -0.57
     VIDEOT
    -0.57
    POSITIVE LOGITS
    #
    0.75
     #
    0.62
     \#
    0.40
    #
    0.39
    \#
    0.36
    #!/
    0.35
    @
    0.34
     okol
    0.34
     any
    0.34
     then
    0.34
    Act Density 0.001%

    No Known Activations