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

    Neuronpedia

    INDEX
    Explanations

    potential

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of technical method terms—especially names or uses of “potentials” (e.g. n-body potential, effective potential, interatomic potential) and similar model descriptors in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     devote
    -0.06
    ()?>
    -0.06
    Band
    -0.06
    -badge
    -0.06
    rdf
    -0.06
    atom
    -0.06
     Shutterstock
    -0.06
    请求
    -0.06
    ılmıştır
    -0.06
    }());↵
    -0.06
    POSITIVE LOGITS
     Saskatchewan
    0.07
    186
    0.06
    เทศ
    0.06
     debit
    0.06
     рецеп
    0.06
     accompl
    0.06
     deline
    0.06
     Peterson
    0.06
    ipeg
    0.06
     Transform
    0.06
    Act Density 0.015%

    No Known Activations