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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens (including integers, decimals, and list-item numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    TypeName
    -0.07
     Charity
    -0.07
    _requires
    -0.06
     Courtesy
    -0.06
     favicon
    -0.06
    cen
    -0.06
    archical
    -0.06
    .enums
    -0.06
    ело
    -0.06
     범
    -0.06
    POSITIVE LOGITS
    (bp
    0.06
    ,list
    0.06
    (sql
    0.06
     Av
    0.06
    .REACT
    0.06
     Adding
    0.06
    .Observable
    0.06
     Rey
    0.06
     rallies
    0.06
    .timezone
    0.06
    Act Density 0.058%

    No Known Activations