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

    Neuronpedia

    INDEX
    Explanations

    brands and products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bla
    0.51
     deviate
    0.41
    iboard
    0.37
     dentist
    0.37
     कक्क
    0.37
    hoo
    0.37
     number
    0.36
    hi
    0.36
     sulphur
    0.36
     cyclist
    0.36
    POSITIVE LOGITS
    品牌
    0.46
    brands
    0.43
     visiteurs
    0.42
     clientes
    0.42
     Brands
    0.42
     Visitors
    0.41
     Doll
    0.39
     Exposed
    0.39
    商品
    0.39
     brands
    0.39
    Act Density 0.004%

    No Known Activations