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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical tokens, spotting numbers and numeric statistics in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     intro
    -0.07
     Payne
    -0.07
     Fernandez
    -0.07
     Game
    -0.07
    params
    -0.07
     reputed
    -0.07
     billboard
    -0.07
     dou
    -0.07
     Sweep
    -0.06
     Graz
    -0.06
    POSITIVE LOGITS
     sqlCommand
    0.08
    indexPath
    0.07
    ')));↵↵
    0.07
     */↵↵↵↵
    0.07
    (namespace
    0.07
    스를
    0.06
     ViewChild
    0.06
     베스트
    0.06
    <usize
    0.06
    .Module
    0.06
    Act Density 0.182%

    No Known Activations