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

    Neuronpedia

    INDEX
    Explanations

    preposition followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     моих
    0.39
     seinen
    0.38
     unor
    0.37
     इनसे
    0.35
    कुछ
    0.35
     seines
    0.35
     ваших
    0.35
    これは
    0.34
    某些
    0.34
    これが
    0.34
    POSITIVE LOGITS
     उक्त
    0.68
    該
    0.68
     the
    0.64
    该
    0.59
     উক্ত
    0.53
     该
    0.53
    the
    0.50
     ওই
    0.46
     ئەو
    0.44
     teh
    0.42
    Act Density 0.126%

    No Known Activations