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

    Neuronpedia

    INDEX
    Explanations

    "an" ending or "an" sound

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gew
    1.78
    gens
    1.69
    tes
    1.56
    ीय
    1.54
    trap
    1.43
    salir
    1.41
    tra
    1.39
    gian
    1.39
    дің
    1.38
    daten
    1.36
    POSITIVE LOGITS
    ufact
    1.77
    ্দ্র
    1.71
    ergy
    1.70
    ‍♀️
    1.69
    lı
    1.69
    oramic
    1.68
    으로
    1.67
    ne
    1.65
    ishing
    1.61
    ্ধ্য
    1.60
    Act Density 0.537%

    No Known Activations