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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     u
    -0.07
     AM
    -0.07
     века
    -0.07
    投入使用
    -0.07
     niệm
    -0.07
    Used
    -0.07
     Perry
    -0.07
    喻
    -0.07
     West
    -0.07
     peace
    -0.06
    POSITIVE LOGITS
    ++];↵
    0.07
    极高
    0.07
    (cors
    0.07
     Toastr
    0.06
    formatted
    0.06
    グラ
    0.06
    ++]
    0.06
    افت
    0.06
    0.06
    )(((
    0.06
    Act Density 0.002%

    No Known Activations