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

    Neuronpedia

    INDEX
    Explanations

    code snippet delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.49
     ت
    0.46
    、
    0.46
    ،
    0.44
    ندر
    0.43
    డీపీ
    0.42
    скетбол
    0.42
    导航
    0.41
    <0x80>
    0.41
    ”،
    0.41
    POSITIVE LOGITS
    g
    0.49
    l
    0.48
    u
    0.47
    b
    0.46
    i
    0.46
     perennial
    0.45
    in
    0.44
    the
    0.44
    a
    0.44
    る
    0.41
    Act Density 0.298%

    No Known Activations