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

    Neuronpedia

    INDEX
    Explanations

    terms related to discrimination based on gender and sexual orientation

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

    Demographics after "of," "or," or different

    np_acts-logits-general · gemini-2.0-flash

    race, gender, age, religion, nationality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.74
     برانيه
    -0.73
    astify
    -0.61
    ngdoc
    -0.59
    ProgressHUD
    -0.56
     فريبيس
    -0.56
    Ligações
    -0.56
    ]<<"
    -0.56
    Pranala
    -0.55
    TagHelper
    -0.55
    POSITIVE LOGITS
     race
    1.44
     gender
    1.35
     nationality
    1.35
     ethnicity
    1.35
     religion
    1.14
    race
    1.10
     age
    1.09
     Race
    1.07
     Ethnicity
    1.03
    Race
    1.01
    Act Density 0.494%

    No Known Activations