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

    Neuronpedia

    INDEX
    Explanations

    Boehner

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of political leaders by title and name (e.g. “Speaker John Boehner,” “Senate Majority Leader Harry Reid,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     گرفت
    -0.06
    -0.06
     "\">
    -0.06
     آموزش
    -0.06
     *,
    -0.06
    矿
    -0.06
     dày
    -0.06
    ---------------
    -0.06
     Ζ
    -0.06
     murderer
    -0.05
    POSITIVE LOGITS
     Boehner
    0.09
     Pelosi
    0.07
     Congressman
    0.07
     McConnell
    0.07
     bang
    0.07
    DBNull
    0.07
    าหล
    0.07
    ivor
    0.06
    immel
    0.06
    ncy
    0.06
    Act Density 0.003%

    No Known Activations