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

    Neuronpedia

    INDEX
    Explanations

    continued advancements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erstes
    0.46
     pertama
    0.46
     plötzlich
    0.45
    最初に
    0.43
     suddenly
    0.43
     sudden
    0.42
     позднее
    0.42
    後に
    0.41
     вдруг
    0.41
    tic
    0.40
    POSITIVE LOGITS
     المزيد
    1.45
     further
    1.38
     مزید
    1.33
     weitere
    1.30
    继续
    1.26
    さらに
    1.24
     continue
    1.23
    繼續
    1.23
    Further
    1.21
     আরও
    1.20
    Act Density 0.063%

    No Known Activations