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

    Neuronpedia

    INDEX
    Explanations

    little girl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.36
    在
    0.33
    ),
    0.33
     unserer
    0.32
     शैक्षणिक
    0.32
     Warsz
    0.31
    {\
    0.31
     Phương
    0.31
     },
    0.31
     Gün
    0.31
    POSITIVE LOGITS
    ᧐
    0.35
     pavattati
    0.32
    ⅼ
    0.31
     maken
    0.30
    ߋ
    0.30
    ⲟ
    0.30
    ԁ
    0.29
     marketers
    0.29
     کنی
    0.29
     puedas
    0.28
    Act Density 0.000%

    No Known Activations