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

    Neuronpedia

    INDEX
    Explanations

    misogyny and misogynistic language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inequality
    0.51
     Inequality
    0.46
     polyg
    0.45
     Sheep
    0.40
    ropole
    0.40
     wives
    0.40
     Focusing
    0.39
     focussing
    0.39
     focusing
    0.38
    лари
    0.38
    POSITIVE LOGITS
    noir
    0.44
    oir
    0.41
     Savo
    0.41
     நிர்
    0.40
    вена
    0.40
     nicotin
    0.40
    żli
    0.40
     abilit
    0.40
     बचाया
    0.39
    soir
    0.39
    Act Density 0.001%

    No Known Activations