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

    Neuronpedia

    INDEX
    Explanations

    assembly

    np_max-act · gemini-2.0-flash

    The neuron activates on XML attribute names and values—particularly namespace (xmlns) and assembly declarations—in markup documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     допомоги
    -0.06
    ¸
    -0.06
    riangle
    -0.06
     reversed
    -0.06
    シェ
    -0.06
     reversing
    -0.06
     shoulder
    -0.05
    _company
    -0.05
     rim
    -0.05
    (It
    -0.05
    POSITIVE LOGITS
    tain
    0.07
     sparing
    0.07
    ains
    0.07
     MOVE
    0.07
     tarih
    0.07
    مو
    0.06
     Whole
    0.06
     Opportunity
    0.06
    Assertion
    0.06
     Donate
    0.06
    Act Density 0.004%

    No Known Activations