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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects U.S. district‐court jurisdiction names (i.e. the state/region labels in the court heading).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lent
    -0.07
     Caldwell
    -0.06
    젠
    -0.06
    (cap
    -0.06
     Calder
    -0.06
     Archer
    -0.06
    aku
    -0.06
    цеп
    -0.06
     OBS
    -0.06
    tracker
    -0.06
    POSITIVE LOGITS
     ////
    0.07
    默认
    0.07
     OpenGL
    0.06
     ustanov
    0.06
    ltre
    0.06
    _insert
    0.06
     년
    0.06
     февраля
    0.06
     Scotland
    0.06
     atau
    0.06
    Act Density 0.002%

    No Known Activations