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

    Neuronpedia

    INDEX
    Explanations

    order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     promulgate
    0.40
    sächlich
    0.40
    迪士
    0.40
    мія
    0.39
    พาะ
    0.38
    。...
    0.38
     monadic
    0.38
    ဲ
    0.38
     corne
    0.37
    ंदा
    0.37
    POSITIVE LOGITS
     Mighty
    0.39
     Gorge
    0.38
     Bos
    0.38
     House
    0.38
    0.38
    FAQs
    0.37
     Merced
    0.37
     Morocco
    0.37
     Motorsport
    0.37
     Kras
    0.36
    Act Density 0.003%

    No Known Activations