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

    Neuronpedia

    INDEX
    Explanations

    references to gender identity and the inclusion of diverse gender representations

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

    gender and identity

    np_acts-logits-general · gemini-2.0-flash

    gender identity and expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.68
    ########.
    -0.61
    Xna
    -0.60
     Roskov
    -0.60
     Urheber
    -0.58
    DockStyle
    -0.57
    ngdoc
    -0.56
    ChildScrollView
    -0.55
     للمعارف
    -0.54
    DoubleQuotes
    -0.54
    POSITIVE LOGITS
     gender
    1.24
     trans
    1.13
     transgender
    1.11
     Gender
    1.10
    gender
    1.05
     pronouns
    1.04
    Gender
    1.02
    trans
    0.94
     Trans
    0.91
     transitioning
    0.90
    Act Density 0.147%

    No Known Activations