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

    Neuronpedia

    INDEX
    Explanations

    extra spaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Madison
    -0.08
     epistem
    -0.08
     Lincoln
    -0.08
     Roosevelt
    -0.08
     Chico
    -0.08
     lés
    -0.08
    λού
    -0.08
     willing
    -0.08
     Jackie
    -0.07
     metr
    -0.07
    POSITIVE LOGITS
     commas
    0.09
     whitespace
    0.09
     inaccuracies
    0.09
    字符
    0.08
     excessive
    0.08
    (',',
    0.08
     ',
    0.08
     CSV
    0.08
     comma
    0.08
     newline
    0.08
    Act Density 0.016%

    No Known Activations