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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifs
    -0.07
     incarnation
    -0.06
     medals
    -0.06
    出现
    -0.06
    .parentNode
    -0.06
     Plat
    -0.06
    /tos
    -0.06
    ്�
    -0.06
    パ
    -0.06
    抵
    -0.06
    POSITIVE LOGITS
     Vaughan
    0.07
     csvfile
    0.06
    /File
    0.06
     موقع
    0.06
    ")),
    0.06
    核心
    0.06
    (coder
    0.06
     ответствен
    0.06
     Further
    0.06
    ]:↵↵↵
    0.06
    Act Density 0.003%

    No Known Activations