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

    Neuronpedia

    INDEX
    Explanations

    references to health-related issues and gender comparisons

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

    Male gender and relationships

    np_acts-logits-general · gemini-2.0-flash

    references to men

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wife
    -0.95
     istrinya
    -0.95
    wife
    -0.89
     girlfriend
    -0.81
     Wife
    -0.81
     wives
    -0.80
    setVerticalGroup
    -0.78
    Wife
    -0.77
     woman
    -0.76
     Ms
    -0.76
    POSITIVE LOGITS
     male
    1.27
     husband
    1.25
     husbands
    1.17
     suaminya
    1.15
     males
    1.14
    husband
    1.10
     Husband
    1.08
     boyfriend
    1.08
     masculina
    1.06
     gentlemen
    1.05
    Act Density 0.473%

    No Known Activations