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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。这
    -0.07
    пон
    -0.07
    。她
    -0.07
     ขาย
    -0.06
    _bg
    -0.06
     одне
    -0.06
     ।↵
    -0.06
     birik
    -0.06
    aty
    -0.06
    rocessing
    -0.06
    POSITIVE LOGITS
    _Em
    0.06
    amm
    0.06
     TO
    0.06
     Tmax
    0.06
    #pragma
    0.06
    猫
    0.06
     Grandma
    0.06
    entreprise
    0.06
    _vertices
    0.06
    ordinates
    0.06
    Act Density 0.000%

    No Known Activations