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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lul
    -0.07
    (xhr
    -0.07
     reap
    -0.06
    nga
    -0.06
     BIN
    -0.06
     ioutil
    -0.06
     shard
    -0.06
     ApplicationUser
    -0.06
     pz
    -0.06
       
    -0.06
    POSITIVE LOGITS
    yy
    0.07
     directory
    0.06
    Tex
    0.06
    isi
    0.06
     neck
    0.06
    -network
    0.06
     García
    0.06
     pixels
    0.06
    TeX
    0.06
    -windows
    0.06
    Act Density 0.000%

    No Known Activations