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

    Neuronpedia

    INDEX
    Explanations

    small sample sizes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ету
    -0.07
     цвет
    -0.07
    .Keyboard
    -0.06
     사이
    -0.06
     переда
    -0.06
    ерв
    -0.06
    Tank
    -0.06
    nestjs
    -0.06
    _stride
    -0.06
    hesion
    -0.06
    POSITIVE LOGITS
     "
↵
    0.06
    {↵
    0.06
     erh
    0.06
     Giá
    0.06
     proven
    0.06
     finally
    0.06
    {\
    0.06
    ],[-
    0.06
     والإ
    0.06
    属性
    0.06
    Act Density 0.011%

    No Known Activations