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

    Neuronpedia

    INDEX
    Explanations

    cards, calcium, visa, streets, earn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     daje
    0.46
    信頼
    0.45
    ه‌ها
    0.45
    하다
    0.43
     manca
    0.43
     comprende
    0.43
     conosco
    0.42
     kerajaan
    0.41
     connaît
    0.41
    သား
    0.41
    POSITIVE LOGITS
     is
    0.68
     inorder
    0.50
     inverter
    0.49
    I
    0.49
    X
    0.48
     invertible
    0.48
     আইডি
    0.47
     in
    0.46
     ట
    0.46
     отрима
    0.46
    Act Density 0.000%

    No Known Activations