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

    Neuronpedia

    INDEX
    Explanations

    united

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the word “United,” most often when it appears as part of “United States” in court heading or citation contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     باش
    -0.07
     免
    -0.07
     neigh
    -0.07
     vem
    -0.06
    .Member
    -0.06
     bắt
    -0.06
     контроль
    -0.06
     mistakes
    -0.06
    存在
    -0.06
     nấu
    -0.06
    POSITIVE LOGITS
    _sequence
    0.07
    Pub
    0.06
    .yahoo
    0.06
     oud
    0.06
    than
    0.06
    onis
    0.06
     EQUI
    0.06
     coeffs
    0.06
    ksam
    0.06
    Room
    0.06
    Act Density 0.010%

    No Known Activations