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
     doktor
    -0.06
     fertile
    -0.06
    小说
    -0.06
    ).↵↵
    -0.06
     Jana
    -0.06
    اشی
    -0.06
    ⌒
    -0.06
    closing
    -0.06
    ा.
    -0.06
    _schema
    -0.06
    POSITIVE LOGITS
     mixer
    0.07
     neur
    0.07
     permission
    0.07
     ward
    0.07
    .Permission
    0.06
    nav
    0.06
    _ln
    0.06
    pad
    0.06
    _IN
    0.06
    generation
    0.06
    Act Density 0.000%

    No Known Activations