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

    Neuronpedia

    INDEX
    Explanations

    Articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (parser
    -0.07
     known
    -0.06
    问题
    -0.06
     Verification
    -0.06
    Elem
    -0.06
    .Fetch
    -0.06
     shows
    -0.06
     satu
    -0.06
    Interesting
    -0.06
    색
    -0.06
    POSITIVE LOGITS
    олева
    0.07
     dismay
    0.07
     buen
    0.06
     Fits
    0.06
    posal
    0.06
     Fern
    0.06
    emode
    0.06
    链接
    0.05
     BED
    0.05
     CGI
    0.05
    Act Density 0.026%

    No Known Activations