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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens that are part of date/time values (e.g. timestamps or datetime literals) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rum
    -0.07
    ศจ
    -0.07
     Serve
    -0.06
    -account
    -0.06
    esti
    -0.06
    .String
    -0.06
    Appearance
    -0.06
    ncmp
    -0.06
     περισσότε
    -0.06
    .hash
    -0.06
    POSITIVE LOGITS
     nhắc
    0.08
     Comedy
    0.06
     profitability
    0.06
    _pitch
    0.06
     інш
    0.06
    xFC
    0.06
    :semicolon
    0.06
     ediyor
    0.06
     adhere
    0.06
     classname
    0.06
    Act Density 0.014%

    No Known Activations