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

    Neuronpedia

    INDEX
    Explanations

    references to code components and their functionalities within a software or programming context

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

    programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.73
     Италијани
    -0.72
     kasarigan
    -0.68
    tagHelperRunner
    -0.65
    rrggbb
    -0.61
    HtmlAttribute
    -0.60
     noDo
    -0.60
    endregion
    -0.58
    ьаж
    -0.57
    IndentedString
    -0.57
    POSITIVE LOGITS
     campamento
    0.47
     zwycię
    0.43
     mężczy
    0.40
     Züge
    0.40
     nyingi
    0.40
     voisins
    0.39
     ilustracja
    0.39
     loja
    0.38
     gezicht
    0.37
     escalera
    0.37
    Act Density 0.013%

    No Known Activations