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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    the presence of numeric or number‐like tokens (digits, dates, statistics, decimals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Sultan
    -0.07
     Dropbox
    -0.07
    ittings
    -0.06
    .:.:.:.:.:.:.:.:.:.:.:.:.:.:.:.:
    -0.06
    .RegularExpressions
    -0.06
    ,\"
    -0.06
    textView
    -0.06
     شهرستان
    -0.06
    โป
    -0.06
    usp
    -0.06
    POSITIVE LOGITS
    特色
    0.07
    bie
    0.07
     начала
    0.07
    (Html
    0.06
     intertw
    0.06
    !$
    0.06
     Adds
    0.06
    Featured
    0.06
     sosyal
    0.06
     Zw
    0.06
    Act Density 0.049%

    No Known Activations