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

    Neuronpedia

    INDEX
    Explanations

    Stock tickers

    np_max-act · gemini-2.0-flash

    This neuron detects sequences of uppercase letters (stock ticker symbols) that appear—often in parentheses—after company names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .words
    -0.07
    ########################################################
    -0.07
     -(
    -0.07
     rock
    -0.07
    :::
    -0.07
    _NEW
    -0.07
     Percentage
    -0.07
    Keyword
    -0.07
    -even
    -0.07
     словами
    -0.07
    POSITIVE LOGITS
    -auth
    0.07
    =query
    0.07
     behaviours
    0.07
    TRS
    0.06
    रत
    0.06
    内の
    0.06
     лютого
    0.06
     Fellow
    0.06
     interfer
    0.06
     注
    0.06
    Act Density 0.005%

    No Known Activations