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

    Neuronpedia

    INDEX
    Explanations

    prejudice and discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tAux
    0.47
     ווי
    0.43
     اللا
    0.41
    तिम
    0.39
    AppConstant
    0.39
     SCA
    0.39
    ကောင်း
    0.38
     mam
    0.37
     parton
    0.37
    亿
    0.37
    POSITIVE LOGITS
    rophot
    0.41
    uah
    0.38
    dessus
    0.38
    ද්
    0.36
    上方
    0.36
    ணுவ
    0.36
    coffee
    0.36
    o
    0.36
    due
    0.36
    篆
    0.35
    Act Density 0.000%

    No Known Activations