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

    Neuronpedia

    INDEX
    Explanations

    breast milk jobs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Liet
    0.33
    ‌ها
    0.31
    ９
    0.31
    ستين
    0.30
    ंपा
    0.30
    ંગી
    0.30
    皘
    0.29
     boots
    0.28
     الأد
    0.28
    =’
    0.28
    POSITIVE LOGITS
     Breast
    0.30
    可愛い
    0.28
    Milk
    0.27
     Milk
    0.27
     Bridal
    0.26
     Lorsque
    0.25
     শর্ত
    0.25
     coniferous
    0.25
     ঘি
    0.25
     breast
    0.25
    Act Density 0.260%

    No Known Activations