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

    Neuronpedia

    INDEX
    Explanations

    Numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oni
    -0.07
    .testng
    -0.07
    .Elapsed
    -0.06
    -inv
    -0.06
    ovou
    -0.06
    :::
    -0.06
    Presence
    -0.06
     Faith
    -0.06
    емые
    -0.06
     здат
    -0.06
    POSITIVE LOGITS
     Napoleon
    0.07
    患
    0.06
    ._
    0.06
     DSL
    0.06
     rozh
    0.06
     Junk
    0.06
    ΄
    0.06
    	opts
    0.06
    muz
    0.06
          ↵      ↵
    0.06
    Act Density 0.018%

    No Known Activations