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

    Neuronpedia

    INDEX
    Explanations

    working late

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이죠
    0.46
     যাচ্ছেন
    0.43
     Input
    0.42
    encji
    0.42
     বিপরীতে
    0.42
     impeding
    0.42
     liczba
    0.42
     disequ
    0.42
     impedance
    0.41
    ﺼ
    0.41
    POSITIVE LOGITS
    ibilities
    0.44
     बेटर
    0.43
    ummers
    0.41
    वां
    0.41
    нен
    0.40
     सर्वोत्तम
    0.40
    гов
    0.40
    œurs
    0.40
     well
    0.40
     ули
    0.39
    Act Density 0.008%

    No Known Activations