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

    Neuronpedia

    INDEX
    Explanations

    Western

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tut
    -0.07
    _OUT
    -0.07
    ่านมา
    -0.07
     bunun
    -0.06
     краї
    -0.06
     cháy
    -0.06
    容
    -0.06
     ICC
    -0.06
     schö
    -0.06
     Japon
    -0.06
    POSITIVE LOGITS
     Western
    0.08
     western
    0.08
    Western
    0.08
    jpeg
    0.07
     reopening
    0.06
     exiting
    0.06
     cartesian
    0.06
    ій
    0.06
     WebElement
    0.06
    ajaran
    0.06
    Act Density 0.001%

    No Known Activations