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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    The neuron fires on MongoDB aggregation‐pipeline stage keywords and other `$`-prefixed operators (e.g. `$match`, `$group`, `$project`, `$addFields`, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    IFY
    -0.06
     pasture
    -0.06
     Kil
    -0.06
    筆
    -0.06
    .aspx
    -0.06
    .ci
    -0.06
     отмет
    -0.06
    reed
    -0.06
    _bloc
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    صه
    0.07
    .labelX
    0.07
     Explosion
    0.07
    ){//
    0.06
    oste
    0.06
    На
    0.06
     totalPages
    0.06
    ständ
    0.06
    (Profile
    0.06
    proto
    0.06
    Act Density 0.007%

    No Known Activations