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

    Neuronpedia

    INDEX
    Explanations

    Company abbreviations

    np_max-act · gemini-2.0-flash

    The neuron activates on company/organization name tokens—particularly multi‐word corporate names and their “Co.”/“Ltd.” suffixes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     zaměř
    -0.06
    zkum
    -0.06
     Trey
    -0.06
    幸
    -0.06
     Romantic
    -0.06
     lends
    -0.06
    zech
    -0.06
     Μαρ
    -0.06
    Adds
    -0.06
     Bunun
    -0.06
    POSITIVE LOGITS
     cb
    0.07
    ElementsByTagName
    0.07
     trà
    0.07
    -as
    0.06
     чемпіон
    0.06
    edb
    0.06
     diy
    0.06
    .FindAsync
    0.06
    otify
    0.06
    .Response
    0.06
    Act Density 0.024%

    No Known Activations