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

    Neuronpedia

    INDEX
    Explanations

    the `LICENSE` keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    จะ
    1.79
    ם
    1.73
    이나
    1.71
    ным
    1.68
    ﻕ
    1.64
    은
    1.62
    ன்
    1.50
    ছে
    1.48
    ных
    1.48
    Фу
    1.48
    POSITIVE LOGITS
    ي
    1.88
    y
    1.80
    e
    1.67
    t
    1.63
    eck
    1.51
    т
    1.48
    ei
    1.44
    tp
    1.39
    every
    1.38
    ್ಣ
    1.38
    Act Density 0.000%

    No Known Activations