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

    Neuronpedia

    INDEX
    Explanations

    sexual discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apagos
    0.36
    activeIndex
    0.35
    рец
    0.34
    Bis
    0.33
     અભ
    0.33
     حوال
    0.33
    Murray
    0.33
     খ্রিস্ট
    0.33
     tuyển
    0.33
    ിലാണ്
    0.33
    POSITIVE LOGITS
    模式
    0.45
    部落
    0.40
    秩序
    0.39
    到着
    0.38
     نصی
    0.37
     tribu
    0.37
     Mum
    0.37
     digo
    0.37
     Padua
    0.36
     যুক্তরাষ্ট্রে
    0.36
    Act Density 0.002%

    No Known Activations