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

    Neuronpedia

    INDEX
    Explanations

    degree or quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    П
    0.55
     кстати
    0.49
    ですが
    0.46
     übrigens
    0.45
    Да
    0.45
     или
    0.44
    5
    0.44
    ModelAndView
    0.43
    Мо
    0.43
    Три
    0.43
    POSITIVE LOGITS
     tantos
    0.72
     appunto
    0.66
     tantas
    0.52
    这么多
    0.46
     begitu
    0.45
     এতটা
    0.45
     constantemente
    0.45
     zoveel
    0.45
    歹
    0.44
     necesito
    0.43
    Act Density 0.183%

    No Known Activations