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

    Neuronpedia

    INDEX
    Explanations

    clauses and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bienvenidos
    0.67
     गए
    0.66
    abytes
    0.61
    சனம்
    0.60
    ’!
    0.60
    ड्डी
    0.59
    ণ্ডল
    0.58
    ご覧
    0.58
     числа
    0.58
     saddo
    0.57
    POSITIVE LOGITS
     despite
    1.05
     but
    0.99
     tetapi
    0.97
     while
    0.96
     αλλά
    0.89
     But
    0.87
     जिसमें
    0.87
     nhưng
    0.86
     after
    0.84
     AND
    0.83
    Act Density 1.831%

    No Known Activations