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

    Neuronpedia

    INDEX
    Explanations

    UTF-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    به
    0.73
     (
    0.65
    بد
    0.64
    لي
    0.64
    ب
    0.64
    आई
    0.63
    جي
    0.61
    Pir
    0.61
    رق
    0.61
    SIDE
    0.61
    POSITIVE LOGITS
    น
    0.74
     can
    0.62
    </h3>
    0.62
     they
    0.62
    ágenes
    0.62
     навча
    0.60
     kanilang
    0.59
    耘
    0.58
     reversing
    0.58
     railway
    0.57
    Act Density 0.003%

    No Known Activations