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

    Neuronpedia

    INDEX
    Explanations

    deficiencies in vitamins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    1.14
    ون
    1.13
    .}$
    1.09
    า
    0.97
    of
    0.94
    op
    0.91
    .=
    0.91
    af
    0.90
     Dieses
    0.85
    ais
    0.85
    POSITIVE LOGITS
     အ
    1.02
    เด็ก
    1.00
    麃
    0.94
     prenez
    0.91
     الأ
    0.91
     虽然
    0.91
    詬
    0.91
     हालांकि
    0.90
    鸰
    0.89
     végét
    0.89
    Act Density 0.005%

    No Known Activations