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

    Neuronpedia

    INDEX
    Explanations

    terms related to cars and automotive topics

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

    car and automobile contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Treue
    -0.41
    HandlerContext
    -0.40
     Bühne
    -0.39
     Ruhe
    -0.38
    醒了
    -0.38
     entonces
    -0.38
     ilumina
    -0.37
     Inseln
    -0.35
     rodillas
    -0.35
     jaula
    -0.35
    POSITIVE LOGITS
     cars
    1.02
     car
    0.98
     Cars
    0.97
     Automobile
    0.94
    cars
    0.92
    Cars
    0.91
     automobile
    0.90
     automobiles
    0.88
     Automobiles
    0.86
    Automobile
    0.85
    Act Density 0.028%

    No Known Activations