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

    Neuronpedia

    INDEX
    Explanations

    singly

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens and numeric identifiers (e.g. codes, offsets, IP addresses, port numbers) in technical metadata fields.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     DRAW
    -0.07
     relevance
    -0.06
    óm
    -0.06
     Sensors
    -0.06
    thon
    -0.06
    Sensor
    -0.06
     relevant
    -0.06
     Graf
    -0.06
     predictions
    -0.06
     incentives
    -0.06
    POSITIVE LOGITS
    /cmd
    0.08
     ListViewItem
    0.07
    optimize
    0.07
    yyyyMMdd
    0.07
     "-"↵
    0.07
    (mysql
    0.07
    678
    0.06
     जम
    0.06
    fclose
    0.06
    .reason
    0.06
    Act Density 0.315%

    No Known Activations