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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Kh
    -0.08
    魯
    -0.07
     Papa
    -0.07
    Guide
    -0.07
    =tmp
    -0.07
     arac
    -0.07
     Point
    -0.07
     gio
    -0.06
    pod
    -0.06
     MUT
    -0.06
    POSITIVE LOGITS
     Recruitment
    0.06
     recruitment
    0.06
     alters
    0.06
     dek
    0.06
     поль
    0.06
     #%
    0.06
    股票
    0.06
    ováno
    0.06
    prenom
    0.06
     olmadığı
    0.06
    Act Density 0.004%

    No Known Activations