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

    Neuronpedia

    INDEX
    Explanations

    Medical research texts

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on multi‐letter uppercase abbreviations and acronyms (names of medical tests or procedures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     heat
    -0.07
     shipping
    -0.07
    	grid
    -0.06
     grid
    -0.06
     node
    -0.06
     Heat
    -0.06
     barrel
    -0.06
     granddaughter
    -0.06
     sunk
    -0.06
     firefox
    -0.06
    POSITIVE LOGITS
     Reliable
    0.07
    ınızı
    0.06
    髪
    0.06
    さんの
    0.06
     inflicted
    0.06
     tercer
    0.06
    の上
    0.06
     yerini
    0.06
    \<^
    0.06
     verschill
    0.06
    Act Density 0.069%

    No Known Activations