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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on words that label or introduce items in structured lists or headings (e.g. “policy, education, and training,” “medication‐related factors,” “Access, Action, and Accountability”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ्ध
    -0.07
     Quarry
    -0.07
     نو
    -0.07
    (Link
    -0.07
     fs
    -0.06
    (control
    -0.06
     exciting
    -0.06
     reality
    -0.06
     hotel
    -0.06
    classmethod
    -0.06
    POSITIVE LOGITS
     Dirk
    0.07
    .getLast
    0.07
     Sass
    0.06
     βασ
    0.06
    ==
    0.06
     IList
    0.06
     Palestinians
    0.06
     Melania
    0.06
    :last
    0.06
     osobních
    0.06
    Act Density 0.212%

    No Known Activations