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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Travel
    -0.07
    index
    -0.07
     المش
    -0.07
     Astro
    -0.07
    _source
    -0.07
    slide
    -0.07
    _unused
    -0.07
    dyn
    -0.07
    تط
    -0.07
     защиты
    -0.07
    POSITIVE LOGITS
    뒀
    0.07
     emptied
    0.07
    溦
    0.07
    槚
    0.07
    癗
    0.07
     duż
    0.07
    此案
    0.07
    唵
    0.07
    磜
    0.06
    翙
    0.06
    Act Density 0.004%

    No Known Activations