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

    Neuronpedia

    INDEX
    Explanations

    cooking methods and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     धना
    0.76
    ຢ
    0.70
     ধন
    0.70
    مارات
    0.69
    polyline
    0.69
    pointe
    0.69
     imgSrc
    0.69
    景
    0.69
    字典
    0.68
     proteção
    0.68
    POSITIVE LOGITS
     cooked
    2.38
     cook
    2.25
    Cook
    2.21
     Cook
    2.16
     cooking
    2.01
     boiled
    1.96
    cook
    1.95
    cooked
    1.94
     boil
    1.87
    Cooking
    1.86
    Act Density 0.316%

    No Known Activations