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

    Neuronpedia

    INDEX
    Explanations

    =true

    np_max-act · gemini-2.0-flash

    The neuron fires on the JavaScript URL‐check pattern “is-external=true” (i.e. the substring external=true in the indexOf call).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    stantiate
    -0.07
    謝
    -0.06
     Abr
    -0.06
    .MessageBox
    -0.06
    edar
    -0.06
    creation
    -0.06
    ../../../
    -0.06
     Sung
    -0.06
    divider
    -0.06
    commended
    -0.06
    POSITIVE LOGITS
    _NUMBER
    0.08
    ū
    0.06
    riminal
    0.06
    $fields
    0.06
     okres
    0.06
     duy
    0.06
    m
    0.06
    _MESSAGE
    0.06
     secret
    0.06
     writeln
    0.06
    Act Density 0.003%

    No Known Activations