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

    Neuronpedia

    INDEX
    Explanations

    fiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    1.66
    ться
    1.66
    theless
    1.51
    ्स
    1.45
    不已
    1.45
    ﺙ
    1.41
    ꯟ
    1.38
    WORDS
    1.36
     siehe
    1.33
    дцать
    1.32
    POSITIVE LOGITS
    se
    1.84
    th
    1.39
    Чтобы
    1.37
    ii
    1.36
    Cuál
    1.34
    ~/
    1.32
    רה
    1.29
    it
    1.27
    ynthesis
    1.26
    id
    1.23
    Act Density 0.003%

    No Known Activations