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

    Neuronpedia

    INDEX
    Explanations

    src

    np_max-act · gemini-2.0-flash

    The neuron fires on HTML `<script>` tags—especially when they include external JavaScript via a `src` attribute.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     провед
    -0.07
    KC
    -0.06
     выше
    -0.06
    _scenario
    -0.06
     UNESCO
    -0.06
    Integrated
    -0.06
     Stan
    -0.06
    nen
    -0.06
     sophistication
    -0.06
    Orth
    -0.06
    POSITIVE LOGITS
    atalog
    0.07
     kor
    0.06
     amounted
    0.06
    (PATH
    0.06
    íst
    0.06
    ussion
    0.06
     XB
    0.06
    .'↵↵
    0.06
    emphasis
    0.06
    import
    0.06
    Act Density 0.002%

    No Known Activations