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

    Neuronpedia

    INDEX
    Explanations

    group followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     publice
    1.08
    ırı
    1.05
    अपने
    1.03
     Peu
    1.01
     forhold
    1.01
    शास्त्र
    1.00
     langt
    0.99
     ouvrage
    0.98
     fino
    0.98
     zi
    0.97
    POSITIVE LOGITS
     компаний
    1.63
    think
    1.25
    웨어
    1.23
    𝒐
    1.23
    ድግዳ
    1.19
    atient
    1.17
     بندی
    1.13
     товара
    1.11
    𝙤
    1.09
    াকী
    1.09
    Act Density 0.070%

    No Known Activations