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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software programming and documentation

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

    metathesis reactions and stack traces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hals
    -0.40
     vig
    -0.40
    PostId
    -0.39
     diplo
    -0.39
     dom
    -0.39
     Shar
    -0.39
    Dom
    -0.39
     Hals
    -0.38
     Ned
    -0.38
     Char
    -0.38
    POSITIVE LOGITS
     للمعارف
    0.96
    runApp
    0.90
    ValueStyle
    0.90
    ConverterFactory
    0.89
     BrowserModule
    0.84
    Референце
    0.80
    RectangleBorder
    0.78
    toolbox
    0.78
    ftagPool
    0.75
     estekak
    0.74
    Act Density 0.001%

    No Known Activations