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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emi
    -0.07
    �
    -0.07
    앙
    -0.06
     attachment
    -0.06
     capitalism
    -0.06
    ，他们
    -0.06
     Lynn
    -0.06
    ,\"
    -0.06
     Buffalo
    -0.06
    ifi
    -0.06
    POSITIVE LOGITS
     encrypt
    0.06
    +r
    0.06
    Planning
    0.06
    	en
    0.06
    bufio
    0.06
    =====↵
    0.06
     '_'
    0.06
     formatting
    0.06
     ace
    0.06
     cuent
    0.06
    Act Density 0.095%

    No Known Activations