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

    Neuronpedia

    INDEX
    Explanations

    European names/locations

    np_max-act · gemini-2.0-flash

    This neuron fires on the multi‐syllable capitalized fragments that form place names or territorial designations in aristocratic and noble titles.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     CONCAT
    -0.07
     rpt
    -0.06
     ovšem
    -0.06
    wal
    -0.06
     thác
    -0.06
    .Entities
    -0.06
     знов
    -0.06
    -An
    -0.06
    iê
    -0.06
     rasp
    -0.06
    POSITIVE LOGITS
     &(
    0.07
    period
    0.06
    Describe
    0.06
    ่าม
    0.06
    [offset
    0.06
    478
    0.06
     AUG
    0.06
     conviction
    0.06
     multiplied
    0.06
    (endpoint
    0.06
    Act Density 0.021%

    No Known Activations