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

    Neuronpedia

    INDEX
    Explanations

    grab a quick bite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Restaurant
    0.52
     Restaurant
    0.49
    レストラン
    0.48
     Dinner
    0.48
    料理
    0.46
     dinner
    0.46
     ресторан
    0.45
    餐厅
    0.44
    Furniture
    0.44
    餐廳
    0.43
    POSITIVE LOGITS
     sandwich
    1.21
     sandwiches
    1.11
    sandwich
    1.02
     Sandwich
    1.02
     snack
    1.00
     snacking
    0.89
     snacks
    0.87
     grab
    0.86
    サンド
    0.85
    コンビニ
    0.84
    Act Density 0.027%

    No Known Activations