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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     undercut
    -0.08
    ź
    -0.07
    659
    -0.07
    DETAIL
    -0.07
    Martin
    -0.06
     مسئله
    -0.06
    .assertIn
    -0.06
     переда
    -0.06
     Avery
    -0.06
     :/:
    -0.06
    POSITIVE LOGITS
    δώ
    0.06
    лении
    0.06
     diam
    0.06
    (&_
    0.06
    .translatesAutoresizingMaskIntoConstraints
    0.06
     DI
    0.06
     склада
    0.06
     Spielberg
    0.06
    ább
    0.06
     extr
    0.06
    Act Density 0.008%

    No Known Activations