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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    util
    -0.07
     nước
    -0.07
     functional
    -0.06
     Net
    -0.06
    eygamber
    -0.06
     CDs
    -0.06
     Biological
    -0.06
     salts
    -0.06
     Slovenia
    -0.06
     $"{
    -0.06
    POSITIVE LOGITS
     paginate
    0.07
     subparagraph
    0.07
     Alberta
    0.07
     {}).
    0.06
    :bg
    0.06
    어진
    0.06
    Lastly
    0.06
    《
    0.06
     cotton
    0.06
     section
    0.06
    Act Density 0.106%

    No Known Activations