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

    Neuronpedia

    INDEX
    Explanations

    references to audience engagement and feedback in various contexts

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

    user input and preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iconLine
    -0.60
    IUrlHelper
    -0.60
    ViewImports
    -0.56
    MessageOf
    -0.54
    RenderAtEndOf
    -0.54
    دانشنامهٔ
    -0.54
    delwed
    -0.53
     myſelf
    -0.52
     himſelf
    -0.50
     propOrder
    -0.50
    POSITIVE LOGITS
     favorites
    0.64
     favorite
    0.59
     favourites
    0.58
     favourite
    0.56
    favorite
    0.49
     Favorite
    0.48
     suggestions
    0.47
     votes
    0.46
     FAVORITE
    0.45
    favourite
    0.43
    Act Density 0.032%

    No Known Activations