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

    Neuronpedia

    INDEX
    Explanations

    company leadership

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     edm
    -0.07
     Ronald
    -0.06
    个人
    -0.06
     высок
    -0.06
    Cel
    -0.06
     Mısır
    -0.06
     корот
    -0.06
     druhý
    -0.06
    erton
    -0.06
    Ін
    -0.06
    POSITIVE LOGITS
     🙂
    0.07
     translates
    0.07
     documented
    0.07
     trained
    0.07
    .rectangle
    0.06
    -node
    0.06
    付き
    0.06
    	controller
    0.06
    _Cmd
    0.06
     tpl
    0.06
    Act Density 0.081%

    No Known Activations