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

    Neuronpedia

    INDEX
    Explanations

    mentions dates

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens used in date expressions—month names, day numbers, year numbers, and the surrounding words/punctuation when stating the current date.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ольш
    -0.08
     Bob
    -0.06
     �
    -0.06
     Compression
    -0.06
     planner
    -0.06
    ่ท
    -0.06
    biên
    -0.06
    Publish
    -0.06
    Ms
    -0.06
     illicit
    -0.06
    POSITIVE LOGITS
     screenWidth
    0.07
    .listen
    0.07
    <Class
    0.06
     getResources
    0.06
     بنی
    0.06
    เปอร
    0.06
    =re
    0.06
    (elem
    0.06
    j
    0.06
    .Theme
    0.06
    Act Density 0.048%

    No Known Activations