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

    Neuronpedia

    INDEX
    Explanations

    demonstrate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dř
    0.53
     እንዴት
    0.52
     ವಿಷಯ
    0.50
     усіх
    0.49
     viết
    0.48
     gourd
    0.48
    ність
    0.48
     насо
    0.48
     stran
    0.47
     इंजीनियरिंग
    0.47
    POSITIVE LOGITS
    عت
    0.55
     Neptune
    0.49
    ه‌
    0.49
    دد
    0.47
     Ocean
    0.46
    بد
    0.46
     Provisional
    0.46
     Arg
    0.45
    عرف
    0.43
     Swap
    0.43
    Act Density 0.000%

    No Known Activations