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

    Neuronpedia

    INDEX
    Explanations

    life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PUR
    -0.06
    ?,
    -0.06
    lenme
    -0.06
    압
    -0.06
     Bonnie
    -0.06
    .getP
    -0.06
     assh
    -0.06
    =#{
    -0.06
     Payne
    -0.06
    oins
    -0.06
    POSITIVE LOGITS
    网络
    0.07
     》
    0.06
     theorem
    0.06
    edik
    0.06
    견
    0.06
    .Fragment
    0.06
     reply
    0.06
    (Exception
    0.06
    working
    0.06
     」
    0.06
    Act Density 0.008%

    No Known Activations