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
     unions
    -0.07
    obl
    -0.07
     liter
    -0.06
    allon
    -0.06
     senate
    -0.06
    metry
    -0.06
     idiots
    -0.06
    961
    -0.06
     terör
    -0.06
     setw
    -0.06
    POSITIVE LOGITS
    ModifiedDate
    0.07
    艺
    0.06
    scripts
    0.06
    .Are
    0.06
    んで
    0.06
    -ignore
    0.06
     *)((
    0.06
     котором
    0.06
     tháng
    0.06
    。',↵
    0.06
    Act Density 0.003%

    No Known Activations