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

    Neuronpedia

    INDEX
    Explanations

    Indiana

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    θούν
    -0.07
    ')):↵
    -0.06
     파
    -0.06
     ';
    -0.06
    '},
↵
    -0.06
     malignant
    -0.06
     rinse
    -0.06
     Михай
    -0.06
    _DIM
    -0.06
     라이
    -0.06
    POSITIVE LOGITS
     Indiana
    0.08
    ερ
    0.07
     Billboard
    0.07
    Indiana
    0.06
     XCTestCase
    0.06
     Pence
    0.06
     spoke
    0.06
     appeal
    0.06
     Fraction
    0.06
    мет
    0.06
    Act Density 0.045%

    No Known Activations