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

    Neuronpedia

    INDEX
    Explanations

    curvature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    andas
    -0.07
     cảnh
    -0.07
     trưng
    -0.07
    다는
    -0.07
    strstr
    -0.06
     tornado
    -0.06
    多年
    -0.06
    茫
    -0.06
     puzzled
    -0.06
     indefinite
    -0.06
    POSITIVE LOGITS
    袆
    0.07
    🦸
    0.07
     backlight
    0.07
    (mac
    0.07
    身體
    0.07
    abilities
    0.07
    模具
    0.07
    _Renderer
    0.07
     Raises
    0.07
    價格
    0.06
    Act Density 0.002%

    No Known Activations