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

    Neuronpedia

    INDEX
    Explanations

    book tickets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waging
    0.37
     population
    0.36
     gravity
    0.36
     geological
    0.35
     twist
    0.35
     dialects
    0.35
     genera
    0.35
     प्रच
    0.34
     gener
    0.34
     carbonic
    0.33
    POSITIVE LOGITS
     reservations
    1.15
     reservation
    1.11
     Reservations
    1.02
     réservation
    0.98
     Reservation
    0.98
    予約
    0.98
    reservation
    0.97
     예약
    0.93
    Reservation
    0.93
     आरक्षण
    0.92
    Act Density 0.018%

    No Known Activations