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

    Neuronpedia

    INDEX
    Explanations

    symmetry and asymmetry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䈤
    0.97
     supremum
    0.93
    )[
    0.86
    㐬
    0.86
    ться
    0.84
    㳖
    0.80
     powied
    0.79
    ע
    0.78
     পরিমান
    0.77
    T
    0.77
    POSITIVE LOGITS
    ม
    1.47
    0
    1.29
    at
    1.13
    т
    1.11
    ა
    1.07
    1.02
    !
    0.95
    3
    0.95
    pt
    0.92
    ０
    0.91
    Act Density 0.005%

    No Known Activations