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

    Neuronpedia

    INDEX
    Explanations

    code lists and strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {:
    -0.07
    ISOString
    -0.07
    erce
    -0.07
     Frances
    -0.07
    泛
    -0.07
    纪
    -0.07
    运行
    -0.06
     бути
    -0.06
     Serialization
    -0.06
    [c
    -0.06
    POSITIVE LOGITS
     mil
    0.07
    DTV
    0.07
     california
    0.06
    -che
    0.06
    /M
    0.06
     dot
    0.06
    :url
    0.06
    Liter
    0.06
     госп
    0.06
     поск
    0.06
    Act Density 0.057%

    No Known Activations