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

    Neuronpedia

    INDEX
    Explanations

    flexibility

    np_max-act · gemini-2.0-flash

    This neuron activates on list markers (numbered or bulleted items) indicating the start of an item in a list.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    γέν
    -0.07
    ource
    -0.07
    tracted
    -0.06
    lections
    -0.06
    bish
    -0.06
     Odyssey
    -0.06
    Len
    -0.06
     setState
    -0.06
    -parent
    -0.06
     zombies
    -0.06
    POSITIVE LOGITS
    >//
    0.07
     fragmentManager
    0.07
     |--
    0.06
     Emb
    0.06
    .ge
    0.06
    개의
    0.06
     ALT
    0.06
     женщин
    0.06
     لكل
    0.06
    альную
    0.06
    Act Density 0.003%

    No Known Activations