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

    Neuronpedia

    INDEX
    Explanations

    creation origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ﺍ
    0.73
     និង
    0.72
     was
    0.72
     thiết
    0.70
     ଯ
    0.69
     éta
    0.69
     បាន
    0.66
     nécessaires
    0.66
    odată
    0.64
     etiquetas
    0.64
    POSITIVE LOGITS
    ت
    0.84
    로
    0.75
    स
    0.70
    3
    0.67
    त
    0.66
    8
    0.65
     debugger
    0.62
    ท
    0.61
    т
    0.61
    트
    0.61
    Act Density 0.765%

    No Known Activations