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

    Neuronpedia

    INDEX
    Explanations

    past-tense participles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ആദ്യ
    0.72
    ﺸ
    0.66
     câteva
    0.65
    amending
    0.64
     የመጀመሪያ
    0.64
    ographic
    0.63
     utama
    0.63
     équip
    0.63
     İlk
    0.63
     çünkü
    0.63
    POSITIVE LOGITS
    ت
    1.66
    س
    1.28
    т
    1.20
    ל
    1.19
    و
    1.16
    त
    1.15
    с
    1.07
    з
    1.01
    et
    0.94
    ла
    0.93
    Act Density 0.274%

    No Known Activations