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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bi
    -0.07
    弗
    -0.07
    ัตน
    -0.06
    558
    -0.06
    Gamma
    -0.06
    Psi
    -0.06
     Vic
    -0.06
     blank
    -0.06
     května
    -0.06
     buff
    -0.06
    POSITIVE LOGITS
     order
    0.18
     Order
    0.17
    order
    0.16
    Order
    0.14
     orders
    0.14
    -order
    0.13
     Orders
    0.12
     ordering
    0.12
     ORDER
    0.12
    _Order
    0.12
    Act Density 0.050%

    No Known Activations