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

    Neuronpedia

    INDEX
    Explanations

    future tense, second person verb endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يل
    1.20
    ون
    1.09
    <0x0D>
    1.08
    ா
    1.08
    ا
    0.99
    на
    0.97
    )，
    0.96
    다
    0.96
    )：
    0.86
    す
    0.84
    POSITIVE LOGITS
    n
    1.84
    ig
    1.72
    at
    1.67
    ’
    1.59
    ing
    1.56
    as
    1.45
    al
    1.42
    ”
    1.41
    it
    1.40
    ed
    1.38
    Act Density 0.000%

    No Known Activations