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

    Neuronpedia

    INDEX
    Explanations

    references to vehicles, particularly cars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    car pricing and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.71
     Italijanski
    -0.54
    AndEndTag
    -0.50
     незавершена
    -0.50
    Chham
    -0.47
    جغرافيا
    -0.44
    RegressionTest
    -0.44
    expandindo
    -0.44
    windowFixed
    -0.43
     navideñas
    -0.42
    POSITIVE LOGITS
     Car
    0.48
    Car
    0.47
    car
    0.45
    henswürdigkeiten
    0.45
    CAR
    0.44
     car
    0.43
    ội
    0.42
    cars
    0.41
    Gar
    0.40
     CAR
    0.40
    Act Density 0.001%

    No Known Activations