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

    Neuronpedia

    INDEX
    Explanations

    proper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Desde
    -0.07
    classmethod
    -0.07
     берег
    -0.07
     官
    -0.06
    ')),↵
    -0.06
     cumpl
    -0.06
    Bur
    -0.06
     Du
    -0.06
     lest
    -0.06
    /stretch
    -0.06
    POSITIVE LOGITS
     Error
    0.07
    acağ
    0.06
     flip
    0.06
     giấy
    0.06
     celou
    0.06
    params
    0.06
    -Y
    0.06
     apologies
    0.06
     paz
    0.06
     kicks
    0.06
    Act Density 0.006%

    No Known Activations