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

    Neuronpedia

    INDEX
    Explanations

    process information you give me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    צא
    0.57
    Transaksi
    0.50
    сом
    0.49
    বদ
    0.48
    тук
    0.48
    Traité
    0.46
    如何
    0.46
    战争
    0.46
    <unused1113>
    0.46
     валю
    0.46
    POSITIVE LOGITS
     your
    0.57
     the
    0.55
     approx
    0.49
     engravings
    0.49
     information
    0.49
     aids
    0.48
     buddy
    0.48
     Y
    0.47
     priorities
    0.47
    als
    0.47
    Act Density 0.004%

    No Known Activations