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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens, especially those appearing in addresses or location data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Belarus
    -0.07
     Israel
    -0.06
     mediator
    -0.06
     pans
    -0.06
    Flags
    -0.06
     Delicious
    -0.06
    gypt
    -0.06
     общ
    -0.06
     Employee
    -0.06
    080
    -0.06
    POSITIVE LOGITS
    (setting
    0.07
    InvalidOperationException
    0.07
    Column
    0.06
     vez
    0.06
    :class
    0.06
    .case
    0.06
    \brief
    0.06
    (Component
    0.06
     biç
    0.06
    Cha
    0.06
    Act Density 0.018%

    No Known Activations