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

    Neuronpedia

    INDEX
    Explanations

    references to various car brands and their models

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

    car maker brands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.57
    webElementXpaths
    -0.52
    ectoria
    -0.46
    parsedMessage
    -0.45
     يتيمه
    -0.43
    ContextHolder
    -0.43
     Autorizaciones
    -0.42
    EDEFAULT
    -0.42
    tificial
    -0.42
    localctx
    -0.42
    POSITIVE LOGITS
     automaker
    0.56
     brand
    0.54
     Hyundai
    0.53
     cars
    0.53
     dealerships
    0.52
    roën
    0.51
     Buick
    0.50
     myſelf
    0.49
     automobiles
    0.49
     lópez
    0.49
    Act Density 0.013%

    No Known Activations