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

    Neuronpedia

    INDEX
    Explanations

    values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    股指
    -0.08
    天才
    -0.07
     Benghazi
    -0.07
    资本市场
    -0.07
    RELEASE
    -0.07
    ertility
    -0.07
     организ
    -0.07
    登陆
    -0.07
     risk
    -0.06
    衡阳
    -0.06
    POSITIVE LOGITS
     Arte
    0.07
     dashes
    0.06
    MOTE
    0.06
     sammen
    0.06
    mac
    0.06
     precinct
    0.06
     faction
    0.06
     Cork
    0.06
    @Module
    0.06
    	thread
    0.06
    Act Density 0.013%

    No Known Activations