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

    Neuronpedia

    INDEX
    Explanations

    granting approval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ！"
    -2.55
    🌸
    -2.28
    嫡
    -2.22
    🤑
    -2.17
    ждать
    -2.17
     phenomenal
    -2.06
    ：[
    -2.05
    NOUNC
    -2.00
    -1.98
    with
    -1.97
    POSITIVE LOGITS
    苼
    2.64
          
    2.63
    他们的
    2.45
    稣
    2.36
    2.31
    ...........
    2.28
    十分的
    2.28
     garantia
    2.27
               
    2.23
    綺麗な
    2.23
    Act Density 0.003%

    No Known Activations