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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çözüm
    -0.07
    ود
    -0.07
    nal
    -0.07
     extension
    -0.07
     đo
    -0.06
     desserts
    -0.06
     biến
    -0.06
     öngör
    -0.06
    ナル
    -0.06
    _three
    -0.06
    POSITIVE LOGITS
    (SQL
    0.07
     screenings
    0.06
     reels
    0.06
     seq
    0.06
    inoa
    0.06
    Subscription
    0.06
     Guzzle
    0.06
     revised
    0.06
    _regex
    0.06
    �
    0.06
    Act Density 0.007%

    No Known Activations