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

    Neuronpedia

    INDEX
    Explanations

    asking "why"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    1.63
    اب
    1.30
    И
    1.28
    ى
    1.27
    ни
    1.26
    ת
    1.25
    А
    1.23
    Aunque
    1.20
    Inflation
    1.18
    irà
    1.17
    POSITIVE LOGITS
    곡
    1.39
    냠
    1.33
     libera
    1.17
    ்ய
    1.14
    yyyyyyyy
    1.14
    о
    1.09
    ой
    1.03
    yyyy
    1.02
    暂停
    1.02
    霄
    1.02
    Act Density 0.115%

    No Known Activations