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

    Neuronpedia

    INDEX
    Explanations

    beverages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     기억
    -0.07
     PD
    -0.07
     анализ
    -0.07
     frame
    -0.07
     핵
    -0.07
     unk
    -0.06
     looping
    -0.06
     شاه
    -0.06
     stan
    -0.06
    孔
    -0.06
    POSITIVE LOGITS
     beverages
    0.10
     beverage
    0.09
    _article
    0.08
     Drinks
    0.07
    min
    0.07
     drinks
    0.07
     Beverage
    0.07
    소년
    0.06
    男性
    0.06
    <Renderer
    0.06
    Act Density 0.009%

    No Known Activations