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

    Neuronpedia

    INDEX
    Explanations

    :type

    np_max-act · gemini-2.0-flash

    The neuron fires on XML markup—especially namespace declarations and opening tags.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -max
    -0.07
    Old
    -0.07
    -pres
    -0.06
    Tem
    -0.06
     bake
    -0.06
     Ben
    -0.06
     folklore
    -0.06
     Income
    -0.06
     बद
    -0.06
     bets
    -0.06
    POSITIVE LOGITS
    _resolve
    0.07
     Guam
    0.07
     الجام
    0.07
    ija
    0.07
    \",↵
    0.06
    Returned
    0.06
     достав
    0.06
    (TreeNode
    0.06
    agedList
    0.06
    ="'.
    0.06
    Act Density 0.001%

    No Known Activations