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

    Neuronpedia

    INDEX
    Explanations

    dining out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suicidal
    0.42
     acus
    0.42
     disulfide
    0.41
     suic
    0.40
     lysis
    0.39
     flancs
    0.39
     serialization
    0.39
     payload
    0.38
    ryption
    0.38
     متاب
    0.38
    POSITIVE LOGITS
     restaurants
    0.87
     Restaurants
    0.86
     restaurant
    0.84
     restaurantes
    0.81
     рестора
    0.80
     grocery
    0.79
    Restaurants
    0.79
    restaurants
    0.78
    餐厅
    0.76
     supermarkets
    0.76
    Act Density 0.094%

    No Known Activations