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

    Neuronpedia

    INDEX
    Explanations

    legal cases and people

    np_max-act · gemini-2.0-flash

    The neuron responds primarily to capitalized personal names (proper nouns referring to people).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .ByteString
    -0.07
     ан
    -0.06
    Tips
    -0.06
     smokers
    -0.06
     Leather
    -0.06
    (pe
    -0.06
     sez
    -0.06
     portable
    -0.06
    chers
    -0.06
     अत
    -0.06
    POSITIVE LOGITS
    菲
    0.06
    �
    0.06
    rypton
    0.06
     �
    0.06
    .prompt
    0.06
    -API
    0.06
    twig
    0.06
    フィ
    0.06
     �
    0.06
     Psalm
    0.06
    Act Density 0.034%

    No Known Activations