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
    о
    1.52
    ish
    1.35
    ването
    1.24
     dada
    1.23
    ाई
    1.23
    feito
    1.22
    𝓸
    1.22
    б
    1.21
    твор
    1.20
    ване
    1.20
    POSITIVE LOGITS
     cars
    1.92
    ยนต์
    1.92
     vehicles
    1.84
     locomotives
    1.69
     trucks
    1.69
    輌
    1.67
    汽车
    1.65
    ن
    1.64
    輛
    1.64
     Fahrzeuge
    1.64
    Act Density 0.203%

    No Known Activations