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

    Neuronpedia

    INDEX
    Explanations

    project

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Healthy
    -0.07
    坚守
    -0.07
    感动
    -0.07
     swe
    -0.07
    bp
    -0.07
    老師
    -0.07
     cuid
    -0.06
     Rear
    -0.06
    選び
    -0.06
    Ữ
    -0.06
    POSITIVE LOGITS
    	Config
    0.08
    _AND
    0.08
     //!
    0.07
    ategori
    0.07
     cron
    0.07
     Utils
    0.07
    能力和
    0.07
     brut
    0.07
    换句话说
    0.07
     dragon
    0.07
    Act Density 0.001%

    No Known Activations