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

    Neuronpedia

    INDEX
    Explanations

    medicine related scientific text

    np_max-act · gemini-2.0-flash

    This neuron activates on specialized technical or chemical terminology (e.g. words like “derivatives,” “salts,” “hydrates,” “compounds,” “thrombosis,” “intravascular,” etc.) in patent‐style biomedical text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     visual
    -0.07
     gözlem
    -0.06
    اعة
    -0.06
     businesses
    -0.06
     FETCH
    -0.06
     orally
    -0.06
     *=
    -0.06
    ized
    -0.06
    786
    -0.06
    R
    -0.06
    POSITIVE LOGITS
    оля
    0.07
     solidarity
    0.07
    dn
    0.06
    ropol
    0.06
     reconnect
    0.06
     millennials
    0.06
    �州
    0.06
     pollut
    0.06
     الأس
    0.06
    setImage
    0.06
    Act Density 0.097%

    No Known Activations