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

    Neuronpedia

    INDEX
    Explanations

    food and activity levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     기록
    0.44
    数据的
    0.44
    浗
    0.43
    二维码
    0.42
     रोमांच
    0.41
     cryptography
    0.41
    错
    0.39
    经验
    0.39
    笏
    0.39
     디지털
    0.38
    POSITIVE LOGITS
     meals
    0.75
     fasting
    0.74
     hungry
    0.71
     comedor
    0.69
     meal
    0.68
     snacks
    0.67
     comidas
    0.66
     snacking
    0.66
     breakfast
    0.65
     comida
    0.65
    Act Density 0.129%

    No Known Activations