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

    Neuronpedia

    INDEX
    Explanations

    cars and driving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्रमेय
    0.38
    stractions
    0.37
     Krone
    0.36
     Unicode
    0.35
     unicode
    0.35
    _{+}
    0.35
    ayscale
    0.34
     Kolmogorov
    0.34
    ostic
    0.34
     ஓடுப
    0.33
    POSITIVE LOGITS
     car
    4.09
     cars
    3.33
    car
    3.25
     कार
    3.14
     Car
    3.06
    車
    3.06
    车
    3.05
    Car
    3.03
    cars
    2.86
     Cars
    2.81
    Act Density 0.083%

    No Known Activations