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

    Neuronpedia

    INDEX
    Explanations

    questions and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Islamic
    0.44
     इस्लामिक
    0.41
     ইয়াহিয়া
    0.40
     creciente
    0.40
     শাব
    0.39
     Enhanced
    0.38
     استخدام
    0.38
     realiza
    0.37
     اقول
    0.37
     ইয়াহিয়া
    0.37
    POSITIVE LOGITS
     সুবিধা
    0.46
    বিবি
    0.42
     turist
    0.41
     itinerary
    0.41
    חות
    0.40
     strangers
    0.39
    ynam
    0.39
    itu
    0.38
    ui
    0.38
    Tourist
    0.38
    Act Density 0.008%

    No Known Activations