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

    Neuronpedia

    INDEX
    Explanations

    organizational changes

    np_max-act · gemini-2.0-flash

    specific references to sports teams and their performance statistics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on numeric tokens—especially decimal numbers and monetary figures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    aska
    -0.07
     Ber
    -0.07
    าย
    -0.06
    eggies
    -0.06
     dips
    -0.06
     invisible
    -0.06
    忍
    -0.06
    achs
    -0.06
    adj
    -0.06
     Leisure
    -0.06
    POSITIVE LOGITS
    قم
    0.07
    改革
    0.07
    \Db
    0.07
    OURCES
    0.06
     armored
    0.06
     chod
    0.06
    /config
    0.06
    비아
    0.06
    mě
    0.06
     Columbia
    0.06
    Act Density 0.094%

    No Known Activations