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

    Neuronpedia

    INDEX
    Explanations

    J

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Voll
    -0.07
     azi
    -0.07
     المللی
    -0.06
     明
    -0.06
     uy
    -0.06
    ại
    -0.06
     vztah
    -0.06
     특히
    -0.06
    oll
    -0.06
     voleb
    -0.06
    POSITIVE LOGITS
     JJ
    0.13
    J
    0.13
     JE
    0.12
    ,J
    0.12
     JP
    0.12
     JW
    0.11
     J
    0.11
     JB
    0.11
     JD
    0.11
     JL
    0.11
    Act Density 0.546%

    No Known Activations