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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    The neuron primarily detects standalone colon tokens (":"), marking section labels or headings in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hızla
    -0.07
    uns
    -0.07
    ally
    -0.07
     جه
    -0.07
    ále
    -0.07
    _keyword
    -0.06
    část
    -0.06
    meyi
    -0.06
     ساله
    -0.06
     В
    -0.06
    POSITIVE LOGITS
    奧
    0.07
     dryer
    0.07
     zdję
    0.06
     Bair
    0.06
    Sem
    0.06
     toilets
    0.06
     П
    0.06
    ея
    0.06
    duğ
    0.06
     unlocks
    0.06
    Act Density 0.070%

    No Known Activations