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

    Neuronpedia

    INDEX
    Explanations

    numbers and decimals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    樘
    0.34
    溸
    0.33
    钯
    0.32
    รุ่น
    0.32
    धा
    0.32
    মানুষ
    0.32
    愪
    0.32
    钴
    0.31
    बंग
    0.31
    ន៍
    0.31
    POSITIVE LOGITS
     never
    0.35
     less
    0.34
     five
    0.33
     choice
    0.31
    five
    0.30
     medir
    0.30
     nooit
    0.30
     s
    0.29
     leisten
    0.29
    c
    0.29
    Act Density 0.001%

    No Known Activations