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

    Neuronpedia

    INDEX
    Explanations

    gender roles and equality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grain
    0.35
    san
    0.34
    grep
    0.34
     கல்லறை
    0.34
     период
    0.34
    期間
    0.33
     gobiernos
    0.33
     Period
    0.33
    සා
    0.32
    வீன
    0.32
    POSITIVE LOGITS
     gender
    0.65
     dysph
    0.60
     genders
    0.58
     roles
    0.55
     stereotypes
    0.54
    Gender
    0.52
    gender
    0.52
     relations
    0.50
     Gender
    0.49
     sex
    0.48
    Act Density 0.038%

    No Known Activations