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

    Neuronpedia

    INDEX
    Explanations

    circles; math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     California
    -0.08
     vẻ
    -0.08
    uphoria
    -0.07
     stringify
    -0.07
     bient
    -0.07
     blockbuster
    -0.07
     Hague
    -0.07
     deutlich
    -0.07
    ilean
    -0.07
    curl
    -0.07
    POSITIVE LOGITS
    面积
    0.08
     подпис
    0.08
    .CASCADE
    0.08
    ется
    0.08
    .lookup
    0.07
     centered
    0.07
     perimeter
    0.07
     Lig
    0.07
    #↵↵
    0.07
    <Token
    0.07
    Act Density 0.047%

    No Known Activations