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

    Neuronpedia

    INDEX
    Explanations

    food dishes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sm
    0.75
     cheddar
    0.74
     шокола
    0.73
     Chocolate
    0.73
     مد
    0.73
     Pizza
    0.70
     pizzeria
    0.70
     chocolate
    0.69
    巧克力
    0.68
     chocolat
    0.68
    POSITIVE LOGITS
    ्यूड
    0.82
    mandu
    0.68
     bitter
    0.66
    ListName
    0.65
     ტი
    0.65
     সংগ্রামী
    0.64
     arrogant
    0.63
     wak
    0.63
    pong
    0.61
     საფ
    0.61
    Act Density 0.046%

    No Known Activations