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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to year numbers (dates) in the text, i.e. it activates on tokens representing publication or event years.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Church
    -0.07
    Чер
    -0.06
    Saint
    -0.06
     Lt
    -0.06
    "Yes
    -0.06
    _KEEP
    -0.06
     Elliott
    -0.06
    Gam
    -0.06
     rotten
    -0.06
     collections
    -0.06
    POSITIVE LOGITS
    .writeHead
    0.08
     jadx
    0.07
    نی
    0.07
    =head
    0.07
     in
    0.07
    }',
    0.07
    达
    0.06
     :,
    0.06
    sum
    0.06
     strSql
    0.06
    Act Density 0.100%

    No Known Activations