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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash

    The neuron fires on the semicolon character that begins or appears in code comments (i.e. comment delimiters).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Couch
    -0.07
    形成
    -0.07
     yg
    -0.07
     Hong
    -0.07
     SelectList
    -0.07
     фрон
    -0.07
    onda
    -0.06
    	vo
    -0.06
     $"
    -0.06
     geçmiş
    -0.06
    POSITIVE LOGITS
     standing
    0.06
    .look
    0.06
    lete
    0.06
    esting
    0.06
     stores
    0.06
    송
    0.06
     investor
    0.06
    _invoice
    0.06
    iana
    0.06
     stands
    0.06
    Act Density 0.001%

    No Known Activations