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

    Neuronpedia

    INDEX
    Explanations

    drinks and beverages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    灾
    0.52
     convolutional
    0.49
     ஜனநாயக
    0.49
     нейтро
    0.48
     예측
    0.47
    疥
    0.46
    Crisis
    0.46
    嫄
    0.46
    危机
    0.45
    overty
    0.45
    POSITIVE LOGITS
     drink
    1.72
     beverages
    1.69
     drinks
    1.66
     beverage
    1.59
     Drink
    1.52
     bebida
    1.51
    drink
    1.50
     minuman
    1.50
     bebidas
    1.49
    Drink
    1.48
    Act Density 0.210%

    No Known Activations