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

    Neuronpedia

    INDEX
    Explanations

    national sexual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.33
    માં
    1.32
    ات
    1.19
    ку
    1.09
    يا
    1.05
    يش
    1.03
    كي
    1.02
    ب
    1.00
    ม
    0.98
    ט
    0.98
    POSITIVE LOGITS
    لی
    1.14
    ۰
    1.13
    ূতন
    1.05
    ار
    1.03
    ۵
    0.94
    ong
    0.94
     it
    0.91
    aris
    0.89
    art
    0.88
    ۹
    0.88
    Act Density 0.061%

    No Known Activations