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

    Neuronpedia

    INDEX
    Explanations

    range of examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     divided
    0.47
    多彩
    0.47
     countless
    0.45
     multifaceted
    0.43
     innumerable
    0.42
     variously
    0.42
    divided
    0.41
     Какой
    0.39
     myriad
    0.39
     jeweil
    0.39
    POSITIVE LOGITS
    เพื่อให้
    0.61
     ताकि
    0.58
     zodat
    0.57
     যাতে
    0.56
     علشان
    0.55
     để
    0.52
     opción
    0.52
     כדי
    0.51
     щоб
    0.50
     تاکہ
    0.50
    Act Density 0.001%

    No Known Activations