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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SOLE
    -0.07
     wholesalers
    -0.06
    Even
    -0.06
    Talking
    -0.06
    .active
    -0.06
     отнош
    -0.06
     мень
    -0.06
    困
    -0.06
    Alive
    -0.06
    的声音
    -0.06
    POSITIVE LOGITS
     </>↵
    0.07
    سر
    0.06
     pra
    0.06
     svn
    0.06
     familia
    0.06
    	select
    0.06
    .shows
    0.06
    .this
    0.06
    .’↵↵
    0.06
    :'
    0.06
    Act Density 0.026%

    No Known Activations