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

    Neuronpedia

    INDEX
    Explanations

    skills among

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amplit
    0.79
     wikipedia
    0.77
     medición
    0.76
     इंटरनेट
    0.73
     Bạn
    0.73
     مبنی
    0.72
    網路
    0.72
    交換
    0.71
     Wikipédia
    0.71
     cork
    0.70
    POSITIVE LOGITS
     bagi
    1.00
     belonged
    0.98
     بالنسبة
    0.97
     dla
    0.87
     belongs
    0.86
     targeting
    0.84
     Targeting
    0.80
     belonging
    0.79
    交给
    0.78
     belong
    0.76
    Act Density 1.045%

    No Known Activations