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
     Bounds
    -0.07
     hk
    -0.07
    Checks
    -0.06
    (freq
    -0.06
     compatibility
    -0.06
     Scholarship
    -0.06
    뉴스
    -0.06
     GridView
    -0.06
     [('
    -0.06
     ordeal
    -0.06
    POSITIVE LOGITS
    SUB
    0.07
    100
    0.07
     Exxon
    0.07
     hypo
    0.06
    UNDER
    0.06
    ุลาคม
    0.06
    productos
    0.06
     پی
    0.06
    ویه
    0.06
    )++;↵
    0.06
    Act Density 0.055%

    No Known Activations