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

    Neuronpedia

    INDEX
    Explanations

    acknowledging gratitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тера
    0.74
     لأ
    0.73
     sudd
    0.72
     моих
    0.71
     epigen
    0.70
     можли
    0.70
     margarita
    0.69
     finales
    0.67
     snar
    0.66
     don
    0.66
    POSITIVE LOGITS
    adı
    0.79
    T
    0.71
    驻
    0.71
    يل
    0.70
    تك
    0.70
    \
    0.70
    adb
    0.69
    with
    0.68
    m
    0.68
    婄
    0.68
    Act Density 0.012%

    No Known Activations