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

    Neuronpedia

    INDEX
    Explanations

    elements

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ’nde
    -0.07
     Base
    -0.07
     Account
    -0.07
    (nav
    -0.06
     اوت
    -0.06
     debit
    -0.06
    overlap
    -0.06
    ip
    -0.06
     cellar
    -0.06
    .activity
    -0.06
    POSITIVE LOGITS
    iership
    0.06
     ücretsiz
    0.06
     compuls
    0.06
     irresistible
    0.06
     ethical
    0.06
     useParams
    0.06
     Royals
    0.06
    Salir
    0.06
     […
    0.06
     Dorm
    0.06
    Act Density 0.066%

    No Known Activations