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

    Neuronpedia

    INDEX
    Explanations

    Invest

    np_max-act · gemini-2.0-flash

    The neuron activates on appearance of scientific journal titles (e.g. “Invest,” “J. Clin. Invest,” “Ann. Intern. Med”) in citation strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     collector
    -0.07
     chairs
    -0.07
    expl
    -0.07
     collectors
    -0.07
    数据
    -0.06
    Susan
    -0.06
     acquired
    -0.06
     legends
    -0.06
     Dillon
    -0.06
    ＊
    -0.06
    POSITIVE LOGITS
    破
    0.07
    .CurrentRow
    0.06
    .LayoutControlItem
    0.06
     Computing
    0.06
     Vue
    0.06
     benzer
    0.06
     无
    0.06
     Compared
    0.06
     (!((
    0.06
    (before
    0.06
    Act Density 0.007%

    No Known Activations