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

    Neuronpedia

    INDEX
    Explanations

    enter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hern
    -0.07
     categor
    -0.07
     nghi
    -0.06
     polys
    -0.06
     adoption
    -0.06
    isters
    -0.06
    υσ
    -0.06
    udget
    -0.06
     declar
    -0.06
    .Circle
    -0.06
    POSITIVE LOGITS
    έας
    0.07
    期待
    0.06
    (gcf
    0.06
     �
    0.06
    821
    0.06
     external
    0.06
     External
    0.06
     предпоч
    0.06
    80
    0.06
     ++)↵
    0.06
    Act Density 0.015%

    No Known Activations