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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act · gemini-2.0-flash

    The neuron reliably activates on the opening `<script>` tags (i.e. the start of embedded JavaScript sections).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Odyssey
    -0.07
     함
    -0.06
    -bootstrap
    -0.06
    .visibility
    -0.06
     Fulton
    -0.06
    >\<^
    -0.06
     высок
    -0.06
     داشتن
    -0.06
    jdbc
    -0.06
    .shortcuts
    -0.06
    POSITIVE LOGITS
    (MainActivity
    0.07
    unto
    0.07
    CTYPE
    0.07
     Topics
    0.07
    etí
    0.06
    )];↵
    0.06
     Prob
    0.06
    메
    0.06
    (Route
    0.06
    HomeAsUp
    0.06
    Act Density 0.001%

    No Known Activations