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

    Neuronpedia

    INDEX
    Explanations

    orders and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     기자
    0.71
     plasticity
    0.70
     Ansatz
    0.70
     circuitos
    0.70
     спект
    0.69
    clang
    0.67
     ką
    0.66
    ံ
    0.65
     powierzchni
    0.64
     imparted
    0.64
    POSITIVE LOGITS
     orders
    3.52
     order
    3.51
     Order
    3.28
     Orders
    3.22
    Order
    3.22
    order
    3.13
    orders
    3.10
    Orders
    3.04
     ordering
    3.00
    订单
    2.96
    Act Density 0.260%

    No Known Activations