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

    Neuronpedia

    INDEX
    Explanations

    bar charts and graphs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    и
    2.90
    𝘦
    2.79
    aan
    2.79
    ится
    2.77
    я
    2.72
    ური
    2.71
    ert
    2.67
    ت
    2.64
    gling
    2.60
    𝘮
    2.58
    POSITIVE LOGITS
    ্ষিক
    3.67
    ம்பரிய
    3.49
    ্ষিকী
    2.89
    Мы
    2.72
    뀜
    2.68
    깥
    2.54
     kè
    2.51
     vuoden
    2.50
     consummate
    2.50
    itone
    2.50
    Act Density 0.038%

    No Known Activations