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

    Neuronpedia

    INDEX
    Explanations

    references to male individuals, emphasizing their characteristics or roles

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

    man or guy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theory
    -0.33
     théorie
    -0.32
     Theory
    -0.31
    Geografi
    -0.30
    actéristiques
    -0.30
    евра
    -0.29
     top
    -0.29
    蜻
    -0.28
     thèse
    -0.28
     plongée
    -0.28
    POSITIVE LOGITS
    Hentet
    0.74
    RenderAtEndOf
    0.72
    AndEndTag
    0.71
    AddTagHelper
    0.69
     '\\;'
    0.69
    NameInMap
    0.68
     BoxFit
    0.68
    MLLoader
    0.67
    KommentareTeilen
    0.66
    utilisons
    0.66
    Act Density 0.038%

    No Known Activations