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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ip
    -0.07
    AUT
    -0.07
    _simps
    -0.06
    pile
    -0.06
    Ky
    -0.06
    DAO
    -0.06
     ebp
    -0.06
    .physics
    -0.06
     begging
    -0.06
     verg
    -0.06
    POSITIVE LOGITS
     Magnus
    0.08
     scraper
    0.06
     newcomers
    0.06
    prise
    0.06
    _Buffer
    0.06
     strings
    0.06
     PROCESS
    0.06
    _ACC
    0.06
    .SwingConstants
    0.06
    =↵↵
    0.06
    Act Density 0.012%

    No Known Activations