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

    Neuronpedia

    INDEX
    Explanations

    some followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    きました
    2.36
    ामुळे
    2.03
    ل
    2.02
    ך
    1.98
    te
    1.92
    ння
    1.92
    л
    1.92
    é
    1.88
    дца
    1.87
    不過
    1.81
    POSITIVE LOGITS
    bodies
    2.61
    🅘
    2.27
    f
    2.22
    THING
    2.19
     الشيء
    2.14
    hya
    1.97
    ตรฐาน
    1.97
    מ
    1.95
    a
    1.93
    یه
    1.91
    Act Density 0.309%

    No Known Activations