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

    Neuronpedia

    INDEX
    Explanations

    commands or imperatives related to action and control

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

    commands to *do something*

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     również
    -0.32
     earlier
    -0.29
     early
    -0.29
     vele
    -0.29
     Nación
    -0.28
     investigador
    -0.28
     Both
    -0.28
     także
    -0.28
     later
    -0.27
     underlying
    -0.27
    POSITIVE LOGITS
    AddTagHelper
    0.96
    +#+#
    0.89
    RenderAtEndOf
    0.87
    تقاوى
    0.79
    HtmlAttribute
    0.79
    GIVEREF
    0.77
     للاسماء
    0.73
    IndentedString
    0.72
    argout
    0.72
    Diweddarwch
    0.70
    Act Density 0.095%

    No Known Activations