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

    Neuronpedia

    INDEX
    Explanations

    code splitting; routing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intricate
    -0.08
    _tracker
    -0.07
     ös
    -0.07
     alter
    -0.07
     मुकाब
    -0.07
     disciplin
    -0.07
     evaluator
    -0.07
    _drag
    -0.07
    ushi
    -0.07
     instincts
    -0.07
    POSITIVE LOGITS
     lazy
    0.12
    .lazy
    0.11
    lazy
    0.10
     Lazy
    0.10
    Lazy
    0.09
     laz
    0.09
    _lazy
    0.09
     deferred
    0.08
     Deferred
    0.08
     ahorrar
    0.08
    Act Density 0.002%

    No Known Activations