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

    Neuronpedia

    INDEX
    Explanations

    phone numbers and contact info

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     эти
    0.34
     তারা
    0.34
     αυτά
    0.33
     этого
    0.31
     désormais
    0.29
     αυτή
    0.29
    这些
    0.28
     această
    0.28
     этими
    0.28
    geq
    0.27
    POSITIVE LOGITS
     adduct
    0.26
     کاسینو
    0.26
    하기도
    0.26
    פ
    0.26
     ז
    0.25
     morphisms
    0.25
     prix
    0.25
    ucía
    0.24
    раздо
    0.24
     تماس
    0.23
    Act Density 0.000%

    No Known Activations