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

    Neuronpedia

    INDEX
    Explanations

    Truck driving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spect
    -0.09
     mildew
    -0.08
    spect
    -0.08
     sponge
    -0.08
     downfall
    -0.08
     Spect
    -0.08
     wäre
    -0.08
    .resize
    -0.08
    онь
    -0.08
     abgest
    -0.07
    POSITIVE LOGITS
    司机
    0.16
    驾驶
    0.15
     Fahrer
    0.14
    fahrer
    0.13
     motorista
    0.12
     Driver
    0.12
     drivers
    0.12
    _driver
    0.12
     taxi
    0.11
    老司机
    0.11
    Act Density 0.053%

    No Known Activations