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
     advisors
    -0.07
    $out
    -0.07
     advisers
    -0.07
    ojení
    -0.07
     })
    -0.06
     worldview
    -0.06
    Doctors
    -0.06
     poids
    -0.06
    TextEdit
    -0.06
     พล
    -0.06
    POSITIVE LOGITS
    พ
    0.07
     Breast
    0.06
    ipp
    0.06
    دمة
    0.06
     Skeleton
    0.06
     titanium
    0.06
     ک
    0.06
     измер
    0.06
    岛
    0.06
     《
    0.06
    Act Density 0.002%

    No Known Activations