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

    Neuronpedia

    INDEX
    Explanations

    product quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Keynes
    0.46
     legitimacy
    0.44
    公民
    0.42
     offshoring
    0.42
     हिंसा
    0.41
     bailout
    0.41
     accepted
    0.40
     Fintech
    0.40
     incomes
    0.40
     Accepted
    0.40
    POSITIVE LOGITS
     product
    1.50
    产品
    1.42
    product
    1.38
    产品的
    1.30
     제품
    1.29
    Product
    1.28
     ürün
    1.28
     Product
    1.27
     Produkt
    1.26
     products
    1.24
    Act Density 0.011%

    No Known Activations