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

    Neuronpedia

    INDEX
    Explanations

    Medical studies

    np_max-act · gemini-2.0-flash

    medical treatment outcomes related to surgical procedures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron primarily detects numeric tokens (e.g. counts, percentages, and other statistical figures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _assets
    -0.07
     tes
    -0.07
     exposures
    -0.07
     Kickstarter
    -0.06
     ################################
    -0.06
     Fra
    -0.06
     Tata
    -0.06
     AMC
    -0.06
    .kill
    -0.06
    fatal
    -0.06
    POSITIVE LOGITS
    弄
    0.08
     Synopsis
    0.07
    _buffers
    0.06
    马
    0.06
     (--
    0.06
    ταν
    0.06
    叶
    0.06
     있어
    0.06
    柔
    0.06
    τεί
    0.06
    Act Density 0.058%

    No Known Activations