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

    Neuronpedia

    INDEX
    Explanations

    beer types and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     breweries
    1.10
    brewer
    1.08
    喝酒
    1.06
    啤酒
    1.04
    Brewer
    1.03
    Beer
    1.02
     Brewers
    1.01
     brewery
    1.01
     brewers
    0.99
     Beer
    0.99
    POSITIVE LOGITS
     cream
    1.01
     creme
    0.91
     Cream
    0.90
     Creme
    0.84
     pale
    0.84
     Oatmeal
    0.83
     creamy
    0.82
     creams
    0.81
     smooth
    0.81
    Cream
    0.79
    Act Density 0.012%

    No Known Activations