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

    Neuronpedia

    INDEX
    Explanations

    "one-size-fits-all"

    np_max-act · gemini-2.0-flash

    This neuron activates on parts of hyphenated compound words (i.e. tokens containing hyphens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     것을
    -0.07
    .FragmentManager
    -0.07
    edii
    -0.06
     Trades
    -0.06
    Nb
    -0.06
     해
    -0.06
     chlor
    -0.06
    来了
    -0.06
     André
    -0.06
    fft
    -0.06
    POSITIVE LOGITS
     register
    0.07
    itemid
    0.07
     financed
    0.07
    PING
    0.06
    -flag
    0.06
    REMOTE
    0.06
     Service
    0.06
    .Person
    0.06
     الخامسة
    0.06
     prospect
    0.06
    Act Density 0.001%

    No Known Activations