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

    Neuronpedia

    INDEX
    Explanations

    smart style transfer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >::
    0.40
    rought
    0.38
     kuid
    0.37
    ул
    0.37
     Egyptians
    0.37
    Egy
    0.37
    married
    0.37
    cę
    0.36
    Sie
    0.36
     overlying
    0.36
    POSITIVE LOGITS
     смарт
    0.59
     스마트
    0.58
     स्मार्ट
    0.57
     smart
    0.54
     chatbot
    0.53
     chatbots
    0.52
     smartwatch
    0.52
    スマート
    0.51
     scholarships
    0.51
    chatbot
    0.51
    Act Density 0.000%

    No Known Activations