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

    Neuronpedia

    INDEX
    Explanations

    respectively

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    趣
    -0.08
     어려
    -0.07
    ければ
    -0.07
     sa
    -0.07
    ournal
    -0.07
     sushi
    -0.07
    样的
    -0.06
    ційна
    -0.06
    des
    -0.06
     canned
    -0.06
    POSITIVE LOGITS
     respectively
    0.06
     Lucky
    0.06
     각각
    0.06
     कव
    0.06
     travellers
    0.06
    xbb
    0.06
    ')}}"></
    0.06
    \Exceptions
    0.06
     Invent
    0.06
    AZE
    0.06
    Act Density 0.007%

    No Known Activations