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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     詳細
    -0.07
     在
    -0.07
    рат
    -0.07
     directly
    -0.07
     governmental
    -0.07
    _COMMON
    -0.07
     Isn
    -0.07
    开发
    -0.07
     auditing
    -0.07
    eygamber
    -0.06
    POSITIVE LOGITS
     {
    0.07
     вмі
    0.07
    cron
    0.06
    ऊ
    0.06
     absor
    0.06
     Gle
    0.06
    VMLINUX
    0.06
    IW
    0.06
     Лю
    0.06
    ISON
    0.06
    Act Density 0.002%

    No Known Activations