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

    Neuronpedia

    INDEX
    Explanations

    fact and factual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ށް
    0.43
    ParkingSpot
    0.42
    Wrist
    0.41
    Sil
    0.40
    جیت
    0.40
    Saw
    0.40
    KAM
    0.39
    EI
    0.39
    격을
    0.39
     главного
    0.38
    POSITIVE LOGITS
     facts
    0.88
     фак
    0.72
     Facts
    0.72
    ually
    0.70
     factual
    0.70
    Facts
    0.68
     फैक्ट
    0.68
    事实
    0.67
     fact
    0.67
     Fact
    0.66
    Act Density 0.012%

    No Known Activations