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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vc
    -0.08
     ayr
    -0.06
    (obj
    -0.06
    cook
    -0.06
    -resource
    -0.06
    /renderer
    -0.06
    (thing
    -0.06
    	con
    -0.06
     tracer
    -0.06
    	Time
    -0.06
    POSITIVE LOGITS
    _CODES
    0.07
     keeper
    0.06
    kee
    0.06
    Directed
    0.06
    بلغ
    0.06
    股东
    0.06
    VISION
    0.06
     escalated
    0.06
     끝
    0.06
    かい
    0.06
    Act Density 0.018%

    No Known Activations