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

    Neuronpedia

    INDEX
    Explanations

    Names and citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     traded
    -0.07
     triples
    -0.06
     propose
    -0.06
     fandom
    -0.06
     многих
    -0.06
    orz
    -0.06
    uh
    -0.06
     Catalyst
    -0.06
    “How
    -0.06
     transporter
    -0.06
    POSITIVE LOGITS
     Bernard
    0.07
    -decoration
    0.07
     Hel
    0.07
    ['__
    0.06
     QMainWindow
    0.06
    öff
    0.06
    ?',↵
    0.06
     prosperous
    0.06
     provoked
    0.06
    ิพ
    0.06
    Act Density 0.001%

    No Known Activations