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

    Neuronpedia

    INDEX
    Explanations

    math competition problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     renovations
    -0.09
     Ottoman
    -0.09
     incur
    -0.09
     Joomla
    -0.08
     renovation
    -0.08
     cures
    -0.08
     ISP
    -0.07
     undeniable
    -0.07
    윤
    -0.07
    .Flush
    -0.07
    POSITIVE LOGITS
    _probability
    0.09
    Pak
    0.08
    Probability
    0.08
     fab
    0.08
     राष्ट्रपति
    0.08
     الرسمي
    0.08
     prob
    0.08
     oficiais
    0.08
     Rosal
    0.08
     (![
    0.08
    Act Density 0.011%

    No Known Activations