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

    Neuronpedia

    INDEX
    Explanations

    future

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    制
    -0.07
    请你
    -0.07
     Easter
    -0.07
     established
    -0.07
    民间
    -0.07
    ив
    -0.07
    ileo
    -0.07
     Jinping
    -0.07
    compass
    -0.06
     Ele
    -0.06
    POSITIVE LOGITS
    ❰
    0.07
     maintaining
    0.07
    哥哥
    0.07
    语音
    0.07
    GBK
    0.07
    开盘
    0.06
     �
    0.06
    햇
    0.06
     ההת
    0.06
    🖑
    0.06
    Act Density 0.029%

    No Known Activations