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

    Neuronpedia

    INDEX
    Explanations

    archeology and history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estimator
    -0.07
     asia
    -0.07
    电台
    -0.07
     weak
    -0.07
     boom
    -0.07
    利好
    -0.07
     correspondent
    -0.07
    代言
    -0.06
    ประเทศ
    -0.06
    大涨
    -0.06
    POSITIVE LOGITS
    gesture
    0.07
    욥
    0.07
    安装
    0.07
    ős
    0.06
     orbital
    0.06
    ному
    0.06
    整体
    0.06
     Forget
    0.06
    త
    0.06
     Semantic
    0.06
    Act Density 0.030%

    No Known Activations