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

    Neuronpedia

    INDEX
    Explanations

    specific programming syntax and structural elements

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

    mixed-language technical code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.65
    ⓧ
    -0.65
     Numerade
    -0.61
     NSCoder
    -0.60
    RegressionTest
    -0.57
    styleType
    -0.56
     surla
    -0.54
     Wicidata
    -0.54
     Vikipedi
    -0.53
     GoogleFonts
    -0.52
    POSITIVE LOGITS
    堆
    0.34
     fő
    0.31
    راتيج
    0.29
     виправивши
    0.29
     sets
    0.29
     arrivent
    0.29
     Silber
    0.29
    webElementXpaths
    0.28
    forChild
    0.28
     stack
    0.28
    Act Density 0.356%

    No Known Activations