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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens—i.e. any digits, decimal numbers, percentages, or other number‐containing strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.07
     орг
    -0.06
     endorse
    -0.06
    аний
    -0.06
    idlo
    -0.06
    .EntityFramework
    -0.06
    {{{
    -0.06
    اته
    -0.06
     poised
    -0.06
    encing
    -0.06
    POSITIVE LOGITS
     accidentally
    0.07
    ب
    0.06
    Urban
    0.06
     جنوبی
    0.06
    (Service
    0.06
     placer
    0.06
    Rejected
    0.06
     Namespace
    0.06
     Auto
    0.06
     GridBagConstraints
    0.06
    Act Density 0.253%

    No Known Activations