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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    웤
    -0.07
    keywords
    -0.07
     Code
    -0.07
    网店
    -0.07
    ”.↵↵
    -0.06
    материал
    -0.06
    快三
    -0.06
    ⤶
    -0.06
    CompanyName
    -0.06
    …)↵↵
    -0.06
    POSITIVE LOGITS
     solder
    0.07
     oat
    0.07
     shrimp
    0.07
    _EDGE
    0.07
    .grid
    0.07
    醇
    0.07
     мал
    0.07
     altar
    0.07
     broccoli
    0.07
    风味
    0.07
    Act Density 0.002%

    No Known Activations