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

    Neuronpedia

    INDEX
    Explanations

    occurrences of comment sections and docstring-like structures in code

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

    Python docstring code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -1.23
    StoryboardSegue
    -1.18
    parsedMessage
    -1.16
     CreateTagHelper
    -1.09
    niſſe
    -1.09
     AssemblyCulture
    -1.06
    ConstraintMaker
    -1.05
    CloseOperation
    -1.02
     disambiguazione
    -1.02
     nakalista
    -1.01
    POSITIVE LOGITS
    0
    0.43
    ↵
    0.42
    @
    0.40
    //
    0.39
      
    0.39
    G
    0.39
    ///
    0.39
    :
    0.38
    Y
    0.38
    I
    0.37
    Act Density 0.008%

    No Known Activations