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

    Neuronpedia

    INDEX
    Explanations

    names like Penny, Ruth, kid, fam

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amese
    0.40
    قات
    0.39
    ตร์
    0.39
    和我
    0.39
    cedure
    0.39
    ployed
    0.38
    inkler
    0.38
    ipotent
    0.38
    ੍
    0.38
    teki
    0.37
    POSITIVE LOGITS
     શકાય
    0.46
     сега
    0.45
     competitively
    0.43
     қара
    0.43
     רא
    0.42
     الوزن
    0.42
     ليا
    0.41
     unisex
    0.41
     інтер
    0.41
     ita
    0.41
    Act Density 0.001%

    No Known Activations