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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SDS
    -0.08
    ereal
    -0.08
    incy
    -0.07
    _PLUGIN
    -0.07
    жди
    -0.07
     初始化
    -0.07
    ucus
    -0.07
     Qing
    -0.07
     Sul
    -0.07
    Trademark
    -0.07
    POSITIVE LOGITS
    	cp
    0.07
     he
    0.06
    >");↵
    0.06
     P
    0.06
    communic
    0.06
     dö
    0.06
     với
    0.06
     defiance
    0.05
    ">'+
    0.05
     proced
    0.05
    Act Density 0.023%

    No Known Activations