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

    Neuronpedia

    INDEX
    Explanations

    varied text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    éĽªèĬ±
    -0.29
    isma
    -0.28
     slips
    -0.28
    oning
    -0.27
     Shops
    -0.27
     twisting
    -0.27
    ä¸įæ¸ħ
    -0.27
    æīŃ
    -0.26
    ä¸ĵåĮº
    -0.26
    åħį
    -0.25
    POSITIVE LOGITS
     Nikola
    0.27
     zam
    0.26
     kel
    0.26
    ç»ıèIJ¥ç®¡çIJĨ
    0.26
    ä¸ĭä¸Ģç¯ĩ
    0.26
    iente
    0.25
     Ethiopian
    0.25
    åĩºåĵģ
    0.25
     ott
    0.25
    äºĭãĤĴ
    0.25
    Act Density 0.002%

    No Known Activations