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

    Neuronpedia

    INDEX
    Explanations

    Code/Configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    typename
    -0.07
    珖
    -0.07
    .pnl
    -0.06
    שולחן
    -0.06
     Shawn
    -0.06
    Denied
    -0.06
    noDB
    -0.06
    ᠆
    -0.06
    []
    -0.06
    罔
    -0.06
    POSITIVE LOGITS
     четы
    0.07
     okre
    0.07
     уров
    0.07
     Lehr
    0.06
     Removal
    0.06
     Quản
    0.06
     embr
    0.06
    上课
    0.06
     сохран
    0.06
     этот
    0.06
    Act Density 0.000%

    No Known Activations