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

    Neuronpedia

    INDEX
    Explanations

    df

    np_max-act · gemini-2.0-flash

    The neuron activates on RDF/OWL namespace vocabulary terms (e.g. “rdf,” “rdfs,” “owl,” “xs,” XML namespace tokens)—in other words, it’s detecting RDF schema and ontology prefix declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    counter
    -0.08
     EA
    -0.08
    -Time
    -0.07
     eos
    -0.07
    Bar
    -0.07
     Yao
    -0.07
     علت
    -0.06
    .Stop
    -0.06
     Summers
    -0.06
    )n
    -0.06
    POSITIVE LOGITS
    .rdf
    0.08
    df
    0.08
    rdf
    0.07
     rdf
    0.07
    db
    0.07
    DF
    0.07
    δο
    0.07
    DDL
    0.06
     RDF
    0.06
    xDF
    0.06
    Act Density 0.002%

    No Known Activations