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

    Neuronpedia

    INDEX
    Explanations

    Sweden, MOBILE, Sato, Turkey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agles
    1.12
    Nay
    1.11
    BAT
    1.10
    ONDER
    1.10
    蔽
    1.08
    dodge
    1.07
    dale
    1.07
     BAG
    1.07
    يل
    1.05
     Bag
    1.04
    POSITIVE LOGITS
    ाइयों
    0.94
    wią
    0.78
    ‌
    0.78
    чика
    0.75
     uploaded
    0.74
     Vereins
    0.72
    цией
    0.72
    의
    0.70
     Karim
    0.70
    کام
    0.70
    Act Density 0.015%

    No Known Activations