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

    Neuronpedia

    INDEX
    Explanations

    relief sculptures, carvings, displacement, theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ari
    1.17
    3
    1.13
    la
    1.11
    ri
    1.09
    ling
    1.09
    ंना
    1.08
    ط
    1.08
     as
    1.02
    t
    1.02
    l
    1.02
    POSITIVE LOGITS
     relieved
    1.17
    يس
    1.06
    ير
    1.03
     Relief
    1.00
    、
    0.98
    ،
    0.95
     relief
    0.93
     relieves
    0.92
    سك
    0.90
    زي
    0.88
    Act Density 0.004%

    No Known Activations