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

    Neuronpedia

    INDEX
    Explanations

    spin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     addressing
    -0.08
    竞争优势
    -0.08
     famous
    -0.07
    /mm
    -0.07
    名气
    -0.07
    .nc
    -0.07
    高
    -0.07
    岔
    -0.07
    恐怖
    -0.07
    .Matcher
    -0.07
    POSITIVE LOGITS
    0.07
     같습니다
    0.07
     scans
    0.07
    缠
    0.07
     embedded
    0.07
     SIM
    0.07
     програм
    0.07
    #----------------------------------------------------------------
    0.07
    (plugin
    0.07
    と思っています
    0.07
    Act Density 0.008%

    No Known Activations