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

    Neuronpedia

    INDEX
    Explanations

    instances of formatting or syntactic structure in code snippets

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

    code and language mix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ritz
    -0.46
     covenant
    -0.42
    etCode
    -0.41
    ront
    -0.39
    ,
    -0.38
    newline
    -0.37
    gsub
    -0.36
     bet
    -0.36
    бук
    -0.36
     and
    -0.35
    POSITIVE LOGITS
     disambiguazione
    0.75
    expandindo
    0.69
     AssemblyCulture
    0.66
    Rujuakan
    0.66
    adaptiveStyles
    0.65
     تكبرها
    0.60
    .*")]
    0.57
    HomeAsUpEnabled
    0.56
    ViewFeatures
    0.56
    ьаж
    0.54
    Act Density 0.128%

    No Known Activations