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

    Neuronpedia

    INDEX
    Explanations

    words from diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esque
    1.38
    ième
    1.13
    mice
    1.06
    er
    1.05
    ০
    1.05
    erade
    1.05
    udrait
    1.04
    ي
    1.03
    lains
    1.01
     nhàng
    1.01
    POSITIVE LOGITS
    ल्
    0.89
     acredit
    0.85
    ме
    0.85
     prognosis
    0.85
    ㍍
    0.85
    Ֆ
    0.84
    उसके
    0.84
    ّ
    0.83
    р
    0.83
     Дмитрий
    0.82
    Act Density 0.155%

    No Known Activations