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
    .manager
    -0.07
    _Report
    -0.07
    _STRIP
    -0.07
     температуры
    -0.06
    _waiting
    -0.06
    /display
    -0.06
     precautions
    -0.06
    Earlier
    -0.06
    compiled
    -0.06
    _container
    -0.06
    POSITIVE LOGITS
     reverted
    0.07
    ackers
    0.06
    oklyn
    0.06
     phường
    0.06
     ملف
    0.06
    -app
    0.06
     wäh
    0.06
     SSL
    0.06
    Prog
    0.06
     toto
    0.06
    Act Density 0.057%

    No Known Activations