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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron detects category lines that specify an organization’s establishment year and location (the “<year> establishments in <place>” pattern).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _POLL
    -0.06
     neler
    -0.06
    .RowCount
    -0.06
    SIGN
    -0.06
    .NonNull
    -0.06
     fists
    -0.06
     nails
    -0.06
    (listener
    -0.06
     nextPage
    -0.06
     semble
    -0.06
    POSITIVE LOGITS
    �
    0.07
    (upload
    0.07
     }));↵
    0.06
     parish
    0.06
    oge
    0.06
    ้อง
    0.06
     založ
    0.06
    _Response
    0.06
    prehensive
    0.06
    Publish
    0.06
    Act Density 0.001%

    No Known Activations