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

    Neuronpedia

    INDEX
    Explanations

    sd device

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    checked
    -0.08
    以人为本
    -0.07
     هنا
    -0.07
     Burma
    -0.07
    “As
    -0.06
     x
    -0.06
    (mu
    -0.06
    óm
    -0.06
    -pro
    -0.06
    关键时刻
    -0.06
    POSITIVE LOGITS
    טין
    0.08
    生产和
    0.07
    ...]↵↵
    0.07
     DV
    0.07
     considerably
    0.07
     ReactDOM
    0.07
     rent
    0.07
    受众
    0.06
    鼗
    0.06
    _tracker
    0.06
    Act Density 0.016%

    No Known Activations