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

    Neuronpedia

    INDEX
    Explanations

    months and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protéines
    0.45
     antibiot
    0.45
     albumen
    0.43
     chloride
    0.42
     proteínas
    0.41
     infek
    0.41
     huesos
    0.40
     कण
    0.39
     trastornos
    0.39
     skór
    0.39
    POSITIVE LOGITS
    ချက်
    0.42
    вшей
    0.39
     🤔
    0.37
     Ecommerce
    0.37
    Ecommerce
    0.35
     страхо
    0.35
     ticked
    0.34
     single
    0.34
     подход
    0.33
    quillo
    0.33
    Act Density 0.009%

    No Known Activations