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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    This neuron detects XML digital‐signature markup (e.g. the `<Signature>`, `<SignedInfo>`, `<Transform>`, `<DigestValue>` elements and their attributes).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cellar
    -0.07
     운동
    -0.07
    Soup
    -0.07
    /testing
    -0.06
     meat
    -0.06
    dehy
    -0.06
     Dublin
    -0.06
    HEME
    -0.06
     cooled
    -0.06
     scant
    -0.06
    POSITIVE LOGITS
    ategorie
    0.07
    عة
    0.07
     classNames
    0.06
    اقة
    0.06
    POSITORY
    0.06
     forbid
    0.06
    setLabel
    0.06
    oho
    0.06
    #\
    0.06
     Olymp
    0.06
    Act Density 0.007%

    No Known Activations