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
     characters
    -0.07
     Semaphore
    -0.06
     Slide
    -0.06
     Beaver
    -0.06
     mList
    -0.06
    Characters
    -0.06
    ARCHAR
    -0.06
     jint
    -0.06
     Tacoma
    -0.06
     Unicorn
    -0.06
    POSITIVE LOGITS
    '{
    0.07
    いた
    0.07
    ienda
    0.07
     incons
    0.07
    dük
    0.06
    >>;↵
    0.06
     cryptographic
    0.06
    qn
    0.06
    	en
    0.06
     edecek
    0.06
    Act Density 0.035%

    No Known Activations