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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bur
    -0.07
     zp
    -0.06
    elper
    -0.06
    =["
    -0.06
     ftp
    -0.06
     Devil
    -0.06
     Cem
    -0.06
     dd
    -0.06
    521
    -0.06
     dct
    -0.06
    POSITIVE LOGITS
    imary
    0.06
    (hash
    0.06
    �a
    0.06
    http
    0.06
    міністра
    0.06
    تب
    0.06
    明
    0.06
    /ay
    0.06
    Charset
    0.06
    -reference
    0.06
    Act Density 0.001%

    No Known Activations