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 JSDoc‐style parameter documentation lines (the “– paramName: {Type} description” entries in code comments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    "E
    -0.07
    outh
    -0.07
     blasting
    -0.06
    "C
    -0.06
     ee
    -0.06
     cellFor
    -0.06
     divul
    -0.06
     bul
    -0.06
     spraying
    -0.06
     Kapoor
    -0.06
    POSITIVE LOGITS
    ajax
    0.07
    Ajax
    0.07
    elp
    0.06
    eln
    0.06
     Jupiter
    0.06
    icultural
    0.06
    ubble
    0.06
    relations
    0.06
    Und
    0.06
     observational
    0.06
    Act Density 0.019%

    No Known Activations