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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to individuals, particularly highlighting distinctions between genders

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

    "his or her" or "him/her" constructions

    np_acts-logits-general · gemini-2.0-flash

    gender-inclusive phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URLException
    -0.80
    InitStruct
    -0.73
    WriteAttribute
    -0.72
    elemField
    -0.72
    adaptiveStyles
    -0.72
    RectangleBorder
    -0.71
    IonicModule
    -0.70
    AddTagHelper
    -0.67
    ValueStyle
    -0.67
    DockStyle
    -0.67
    POSITIVE LOGITS
    seamnă
    0.60
    self
    0.54
     oneself
    0.53
    Self
    0.46
    theim
    0.46
     Self
    0.45
    cember
    0.45
     hå
    0.44
    onenumber
    0.43
     gender
    0.43
    Act Density 0.078%

    No Known Activations