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

    Neuronpedia

    INDEX
    Explanations

    size and number of employees/parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spécifiques
    0.41
     spezi
    0.39
     blueberries
    0.39
    だったので
    0.39
    栆
    0.39
     কারণে
    0.39
     специфи
    0.39
    你需要
    0.39
    出现了
    0.38
     Dura
    0.38
    POSITIVE LOGITS
     규모
    0.70
    employees
    0.65
    規模
    0.64
     million
    0.63
     employees
    0.63
    규모
    0.63
    人數
    0.62
     headcount
    0.61
     workforce
    0.58
    人数
    0.58
    Act Density 0.069%

    No Known Activations