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

    Neuronpedia

    INDEX
    Explanations

    contests and features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     самостоятель
    -0.09
     Fing
    -0.08
     exited
    -0.08
     percept
    -0.08
     зар
    -0.07
     ನೀಡಿದ್ದಾರೆ
    -0.07
     obwohl
    -0.07
     yields
    -0.07
     тр
    -0.07
     dispositions
    -0.07
    POSITIVE LOGITS
    掲載
    0.09
     prominently
    0.09
     באתר
    0.08
     Zeitung
    0.08
    Leaderboard
    0.08
     shame
    0.08
     Featured
    0.07
     כח
    0.07
     laminated
    0.07
     newsletter
    0.07
    Act Density 0.048%

    No Known Activations