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

    Neuronpedia

    INDEX
    Explanations

    application

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    drive
    -0.08
     mattered
    -0.08
     drive
    -0.07
     ситуации
    -0.07
     naissance
    -0.07
     занят
    -0.07
    OO
    -0.07
     Drive
    -0.07
     الأداء
    -0.07
    .Exceptions
    -0.07
    POSITIVE LOGITS
    iences
    0.08
    _contents
    0.08
     allez
    0.07
     xmlns
    0.07
    色
    0.07
     içerisinde
    0.07
     choreography
    0.07
    Consum
    0.07
    _manage
    0.07
     encomp
    0.07
    Act Density 0.001%

    No Known Activations