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

    Neuronpedia

    INDEX
    Explanations

    Wales

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asteroids
    -0.07
    inned
    -0.07
    _EDITOR
    -0.07
     transformation
    -0.07
    嗳
    -0.07
    长大
    -0.07
    Thunder
    -0.07
    岭
    -0.07
     Flames
    -0.07
     suffix
    -0.06
    POSITIVE LOGITS
    .PictureBox
    0.07
    _nan
    0.07
    %
↵
    0.07
    جان
    0.07
    حقق
    0.07
    ….
    0.06
    抓
    0.06
    …)↵↵
    0.06
    ゼ
    0.06
    眨
    0.06
    Act Density 0.031%

    No Known Activations