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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron detects XML namespace declaration attributes (e.g. the “xmlns:android=” lines).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    warning
    -0.07
    =zeros
    -0.06
     Tulsa
    -0.06
    median
    -0.06
    神
    -0.06
     gears
    -0.06
     suspend
    -0.06
    _bulk
    -0.06
    REATE
    -0.06
    .result
    -0.06
    POSITIVE LOGITS
     Jays
    0.07
     CrossRef
    0.06
    ина
    0.06
     contentious
    0.06
    Integer
    0.06
     simplement
    0.06
    -play
    0.06
     Surf
    0.06
     Translation
    0.06
    ..........
    0.06
    Act Density 0.002%

    No Known Activations