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

    Neuronpedia

    INDEX
    Explanations

    active or parentheses

    np_max-act · gemini-2.0-flash

    The neuron flags CSS class names in code—especially “current” and “active”—as they appear in selectors or add/removeClass calls.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nuclear
    -0.07
    .clientX
    -0.07
     Alle
    -0.06
    elyn
    -0.06
     fanatic
    -0.06
    ','".$
    -0.06
     Nuclear
    -0.06
    .onChange
    -0.06
     jQuery
    -0.06
    .use
    -0.06
    POSITIVE LOGITS
    赵
    0.06
    !!!↵
    0.06
    宅
    0.06
     CONSEQUENTIAL
    0.06
    Versions
    0.06
    _nom
    0.06
     investigates
    0.06
     convened
    0.06
    _dummy
    0.06
     Pais
    0.06
    Act Density 0.006%

    No Known Activations