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

    Neuronpedia

    INDEX
    Explanations

    Code/markup language

    np_max-act · gemini-2.0-flash

    This neuron activates on XML markup tokens, such as the “<?xml” declaration, element names, and schema‐related tags.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     반
    -0.06
    화를
    -0.06
     texture
    -0.06
    pcodes
    -0.06
    realm
    -0.06
     doors
    -0.06
     glasses
    -0.06
    де
    -0.06
     ш
    -0.06
     креп
    -0.06
    POSITIVE LOGITS
    춘
    0.07
     Huffington
    0.06
    美国
    0.06
    nout
    0.06
     chancellor
    0.06
     тебя
    0.06
     Grow
    0.06
     JsonObject
    0.06
     Profes
    0.06
    merican
    0.06
    Act Density 0.097%

    No Known Activations