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

    Neuronpedia

    INDEX
    Explanations

    password management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    低碳
    -0.08
    .linalg
    -0.07
    头晕
    -0.07
     Mechanical
    -0.07
     letzten
    -0.07
    	vo
    -0.07
    佝
    -0.07
    主题教育
    -0.07
    矿物质
    -0.07
     orchestra
    -0.07
    POSITIVE LOGITS
     posts
    0.07
     month
    0.06
    停止
    0.06
    uction
    0.06
    ➹
    0.06
     naj
    0.06
    辒
    0.06
    רוב
    0.06
    日记
    0.06
     showers
    0.06
    Act Density 0.060%

    No Known Activations