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

    Neuronpedia

    INDEX
    Explanations

    precedes, precede, preceded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.89
    ara
    0.84
    '
    0.80
     istraž
    0.80
     ﺍ
    0.78
     sfrutt
    0.76
     atas
    0.75
     hyvä
    0.74
    "
    0.73
     usare
    0.73
    POSITIVE LOGITS
    ر
    0.84
    ز
    0.78
     precedes
    0.75
     precede
    0.73
    ктак
    0.73
     ہوئی۔
    0.73
     کی۔
    0.72
    i
    0.72
     preceded
    0.71
    т
    0.71
    Act Density 0.088%

    No Known Activations