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

    Neuronpedia

    INDEX
    Explanations

    two items or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     all
    0.68
     ყველა
    0.64
     सबै
    0.62
     всех
    0.61
     kõik
    0.61
     semua
    0.59
     várias
    0.57
     various
    0.54
     allemaal
    0.54
     ಎಲ್ಲ
    0.52
    POSITIVE LOGITS
    这两个
    1.02
     দুটি
    0.96
     beiden
    0.95
     двумя
    0.93
    两个
    0.93
     দুটো
    0.92
    两种
    0.91
    兩個
    0.90
     двох
    0.89
    一个是
    0.89
    Act Density 0.156%

    No Known Activations