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

    Neuronpedia

    INDEX
    Explanations

    topics related to gender roles and societal expectations

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

    Followed by a period/semicolon/comma

    np_acts-logits-general · gemini-2.0-flash

    populations or specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.52
     avoient
    -0.45
     plufieurs
    -0.44
    CodeAttribute
    -0.43
     enseignants
    -0.43
     žaid
    -0.42
     समीक्षक
    -0.42
     étoient
    -0.41
    żesz
    -0.40
    Teacher
    -0.39
    POSITIVE LOGITS
    تقاوى
    0.56
    CreateModel
    0.48
    modelBuilder
    0.47
     يتيمه
    0.46
    ConstraintMaker
    0.46
    ="@+
    0.45
     $__
    0.42
    thâu
    0.42
    
    0.40
     Schles
    0.40
    Act Density 0.554%

    No Known Activations