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

    Neuronpedia

    INDEX
    Explanations

    Answer

    np_max-act · gemini-2.0-flash

    This neuron is tuned to spot tokens made up entirely of contiguous digits (i.e. whole-number strings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    inconsistencies in numerical data presented in summaries compared to original documents.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Items
    -0.07
    警
    -0.07
    كرة
    -0.07
    eos
    -0.06
    (typ
    -0.06
     frontend
    -0.06
    Gre
    -0.06
    INavigationController
    -0.06
     Evelyn
    -0.06
     Attach
    -0.06
    POSITIVE LOGITS
    :NSUTF
    0.07
     standoff
    0.06
     extend
    0.06
     Bengals
    0.06
    ‌المل
    0.06
    ียงใหม
    0.06
    border
    0.06
    bble
    0.06
    mvc
    0.06
    $view
    0.05
    Act Density 0.005%

    No Known Activations