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

    Neuronpedia

    INDEX
    Explanations

    experimental research

    np_max-act · gemini-2.0-flash

    The neuron fires on words signaling experimental or empirical methods (e.g. “experimentally,” “experimental,” “investigated”), marking methodological descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    бина
    -0.07
    gest
    -0.07
     offspring
    -0.06
    واره
    -0.06
     youth
    -0.06
    -types
    -0.06
    (nums
    -0.06
     βά
    -0.06
    PF
    -0.06
    perience
    -0.06
    POSITIVE LOGITS
     embr
    0.07
     عملية
    0.07
     ιστο
    0.07
     legisl
    0.07
    eight
    0.07
     lesbians
    0.06
    .textView
    0.06
     mimo
    0.06
     châu
    0.06
     chuyện
    0.06
    Act Density 0.015%

    No Known Activations