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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	output
    -0.07
     reinstall
    -0.07
     끝
    -0.07
     这
    -0.07
     Blur
    -0.07
     حفظ
    -0.07
     refresh
    -0.07
     таких
    -0.07
     lock
    -0.07
     swept
    -0.06
    POSITIVE LOGITS
    ayd
    0.06
    іш
    0.06
    emons
    0.06
    чим
    0.06
    áln
    0.06
    ome
    0.06
    annie
    0.06
    념
    0.06
     championships
    0.06
    akhstan
    0.06
    Act Density 0.008%

    No Known Activations