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

    Neuronpedia

    INDEX
    Explanations

    learning examples and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     techniques
    0.51
     Filme
    0.49
    یمی
    0.49
    Recipes
    0.49
    U
    0.48
    Methods
    0.48
    Movies
    0.47
    université
    0.46
     methods
    0.46
    اد
    0.45
    POSITIVE LOGITS
     брау
    0.55
     كلا
    0.51
     аккумулятор
    0.50
     computeEncoder
    0.48
    gk
    0.47
     коп
    0.47
     продов
    0.45
     выбо
    0.45
    FragmentManager
    0.45
     полі
    0.45
    Act Density 0.002%

    No Known Activations