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

    Neuronpedia

    INDEX
    Explanations

    was, is, been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ها
    1.30
    ا
    1.13
     কোমল
    1.11
     питание
    1.11
    কে
    1.09
     дости
    1.09
    nya
    1.07
     почвы
    1.06
     enjo
    1.03
    inda
    1.03
    POSITIVE LOGITS
    ем
    1.11
    \%.
    1.07
    SEP
    1.07
     accusing
    1.06
    र्गत
    1.03
    fone
    1.02
    eslint
    1.02
    gather
    1.01
    HttpMethod
    1.00
     nest
    0.97
    Act Density 0.002%

    No Known Activations