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

    Neuronpedia

    INDEX
    Explanations

    discussions about product quality and manufacturing standards

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

    product sold or marketed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.65
     الحره
    -0.64
    CloseOperation
    -0.61
     esternos
    -0.60
    setVerticalGroup
    -0.57
     للمعارف
    -0.55
    dersfield
    -0.55
     المعيارى
    -0.54
    atshirt
    -0.53
     surla
    -0.53
    POSITIVE LOGITS
     manufactured
    0.66
     product
    0.65
     marketed
    0.64
     priced
    0.63
     sold
    0.62
     market
    0.61
     price
    0.59
     Product
    0.58
     selling
    0.58
    product
    0.56
    Act Density 0.048%

    No Known Activations