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

    Neuronpedia

    INDEX
    Explanations

    scientific, technical

    np_max-act · gemini-2.0-flash

    This neuron activates on domain-specific technical nouns and jargon (e.g., specialized multi-syllable content words).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ConfigurationManager
    -0.07
     articles
    -0.06
     article
    -0.06
    Tokenizer
    -0.06
     IDENT
    -0.06
     sizes
    -0.06
     certification
    -0.06
     chuyện
    -0.06
     Matters
    -0.06
    ysize
    -0.06
    POSITIVE LOGITS
     травня
    0.08
    áj
    0.07
    .ImageField
    0.07
    ()=>{↵
    0.07
    liked
    0.06
    oji
    0.06
     arac
    0.06
     allegedly
    0.06
     GWei
    0.06
    loan
    0.06
    Act Density 0.245%

    No Known Activations