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

    Neuronpedia

    INDEX
    Explanations

    vehicles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متر
    -0.08
     roku
    -0.08
    ناة
    -0.08
     incont
    -0.07
     જવ
    -0.07
    ноч
    -0.07
     nuk
    -0.07
     Muhamm
    -0.07
     принима
    -0.07
    ["+
    -0.07
    POSITIVE LOGITS
     onboard
    0.19
     aboard
    0.18
     passengers
    0.14
    Passenger
    0.14
     passageiros
    0.13
    驾驶
    0.12
     Fahrer
    0.12
     passenger
    0.12
    Passengers
    0.11
     Passenger
    0.11
    Act Density 0.127%

    No Known Activations