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

    Neuronpedia

    INDEX
    Explanations

    language articles or determiners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     هذا
    0.97
    一個
    0.97
    一个
    0.93
     남
    0.91
     ein
    0.90
     một
    0.90
    で
    0.89
    ると
    0.89
    the
    0.88
    と
    0.86
    POSITIVE LOGITS
    شارة
    0.77
     situation
    0.75
     guidance
    0.74
     situazione
    0.74
     Vielzahl
    0.73
     considered
    0.73
    ości
    0.72
     situação
    0.69
    ინის
    0.69
     measured
    0.68
    Act Density 0.143%

    No Known Activations