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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects tokens describing corporate or organizational history actions—e.g. acquisitions, mergers, founding or becoming part of another entity.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ologic
    -0.07
     seus
    -0.06
    .JComboBox
    -0.06
    博物
    -0.06
     diagram
    -0.06
     yolc
    -0.06
    sterdam
    -0.06
    ":"'
    -0.06
     Biol
    -0.06
     anarchists
    -0.06
    POSITIVE LOGITS
     gé
    0.06
    mony
    0.06
     steal
    0.06
    ею
    0.06
     Agu
    0.06
    (chars
    0.06
     若要
    0.06
    (elm
    0.06
     initializing
    0.06
     프
    0.06
    Act Density 0.503%

    No Known Activations