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

    Neuronpedia

    INDEX
    Explanations

    references to cars and vehicles

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

    "car" or "cars"

    np_acts-logits-general · gemini-2.0-flash

    cars and vehicles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onders
    -0.55
     Hinton
    -0.49
     Desmond
    -0.49
    unate
    -0.49
     Griffiths
    -0.49
     delights
    -0.48
    roppo
    -0.48
     concise
    -0.48
    >`;
    -0.48
     Delight
    -0.47
    POSITIVE LOGITS
    Car
    0.75
    Vehicle
    0.75
    Cars
    0.73
    Boat
    0.71
    Automobile
    0.70
    cars
    0.70
     Cars
    0.68
    Boats
    0.68
    Airplane
    0.68
     cars
    0.67
    Act Density 0.105%

    No Known Activations