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

    Neuronpedia

    INDEX
    Explanations

    recording

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    million
    -0.08
     tinder
    -0.07
    _we
    -0.07
    ━
    -0.07
    findFirst
    -0.07
     offshore
    -0.07
     của
    -0.07
    ᠰ
    -0.07
    ~-~-
    -0.07
     chu
    -0.07
    POSITIVE LOGITS
     eag
    0.07
    ẹ
    0.07
    鉴定
    0.07
     theater
    0.07
    _pet
    0.06
     ambassador
    0.06
     conspiracy
    0.06
     tired
    0.06
    	URL
    0.06
     pid
    0.06
    Act Density 0.532%

    No Known Activations