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

    Neuronpedia

    INDEX
    Explanations

    make

    np_max-act · gemini-2.0-flash

    The neuron responds broadly to content‐bearing words (nouns, verbs, adjectives) and stays silent on pure function words and punctuation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    orc
    -0.07
     Connect
    -0.06
     connects
    -0.06
    ortal
    -0.06
    tre
    -0.06
    	header
    -0.06
     unserem
    -0.06
    	try
    -0.06
     hmac
    -0.06
    	now
    -0.06
    POSITIVE LOGITS
    Occurrences
    0.07
     #:
    0.06
    แข
    0.06
    broken
    0.06
     Multimedia
    0.06
    -padding
    0.06
     synonymous
    0.06
    _sym
    0.06
     asynchronously
    0.06
    (total
    0.05
    Act Density 0.089%

    No Known Activations