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

    Neuronpedia

    INDEX
    Explanations

    le organisation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nhưng
    0.61
     ancak
    0.55
     également
    0.55
    ेंशन
    0.54
     bianco
    0.54
     ব্যাটিং
    0.54
     ampio
    0.53
     архів
    0.53
     аналоги
    0.53
     pandémie
    0.53
    POSITIVE LOGITS
     to
    0.59
     for
    0.56
    -
    0.56
    '
    0.54
    ار
    0.52
    να
    0.52
     if
    0.50
    5
    0.50
    ы
    0.49
    у
    0.48
    Act Density 0.018%

    No Known Activations