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

    Neuronpedia

    INDEX
    Explanations

    identifying

    np_max-act · gemini-2.0-flash

    The neuron fires on the literal word “tags” in instruction sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ValidateAntiForgeryToken
    -0.06
     XCTAssert
    -0.06
    bling
    -0.06
     proč
    -0.06
    roring
    -0.06
    =com
    -0.06
    annes
    -0.06
    Accuracy
    -0.06
     alacak
    -0.06
     Companies
    -0.06
    POSITIVE LOGITS
    todo
    0.07
     Enumeration
    0.07
     Giul
    0.07
    irmware
    0.07
     fact
    0.07
     KB
    0.06
    (feature
    0.06
     supers
    0.06
    [dim
    0.06
     tiến
    0.06
    Act Density 0.025%

    No Known Activations