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

    Neuronpedia

    INDEX
    Explanations

    y or z

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SQLITE
    -0.07
    ↵	
↵
    -0.06
    слуш
    -0.06
    thed
    -0.06
    enqueue
    -0.06
     Created
    -0.06
    JUnit
    -0.06
     contradict
    -0.06
    等一系列
    -0.06
     nail
    -0.06
    POSITIVE LOGITS
    作坊
    0.07
    enda
    0.07
    (region
    0.07
    进博会
    0.07
    odega
    0.07
    >Description
    0.06
     Rental
    0.06
    势力
    0.06
     pertinent
    0.06
     ',
    0.06
    Act Density 0.013%

    No Known Activations