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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on floating‐point numeric tokens (i.e. numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    amentos
    -0.06
    .Images
    -0.06
     españ
    -0.06
    刷
    -0.06
     koneč
    -0.06
    hp
    -0.06
     被
    -0.06
     Watches
    -0.06
     '[
    -0.06
     lineage
    -0.06
    POSITIVE LOGITS
    _frequency
    0.07
    (value
    0.07
     typing
    0.07
     Plex
    0.07
    owering
    0.07
     sorts
    0.07
    IGHT
    0.06
    іть
    0.06
    .)
    0.06
    ік
    0.06
    Act Density 0.006%

    No Known Activations