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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =========↵
    -0.08
    urple
    -0.07
    헤
    -0.07
    uglify
    -0.07
    Ral
    -0.07
    буд
    -0.06
    urence
    -0.06
    <ul
    -0.06
     Kul
    -0.06
    是国内
    -0.06
    POSITIVE LOGITS
     imperial
    0.07
     источ
    0.07
     Tasks
    0.07
    documento
    0.07
    媭
    0.07
    嫌
    0.07
     PrintWriter
    0.07
    ino
    0.07
     &=
    0.07
    0.07
    Act Density 0.004%

    No Known Activations