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

    Neuronpedia

    INDEX
    Explanations

    File paths and academic publications

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect digit‐and‐punctuation sequences typical of version numbers, DOIs, and other technical identifiers in URLs or file paths.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     оці
    -0.07
    458
    -0.07
     HashMap
    -0.07
    \"></
    -0.07
    ovation
    -0.06
    iculture
    -0.06
    Selector
    -0.06
     pupil
    -0.06
    .framework
    -0.06
    ca
    -0.06
    POSITIVE LOGITS
    metric
    0.06
    (delete
    0.06
    Filed
    0.06
     Estonia
    0.05
    ۸
    0.05
     confirming
    0.05
    لسل
    0.05
     Stanford
    0.05
     STORAGE
    0.05
     Sent
    0.05
    Act Density 0.000%

    No Known Activations