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

    Neuronpedia

    INDEX
    Explanations

    necessities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haus
    -0.06
    ,body
    -0.06
     List
    -0.06
     limit
    -0.06
     Bieber
    -0.06
    CVE
    -0.06
    .lista
    -0.06
     blackjack
    -0.06
     adc
    -0.06
    List
    -0.06
    POSITIVE LOGITS
     lệ
    0.06
     HELP
    0.06
     дир
    0.06
     між
    0.06
    бря
    0.06
     Winning
    0.06
    озмож
    0.06
    abis
    0.06
     skept
    0.06
     superhero
    0.06
    Act Density 0.102%

    No Known Activations