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

    Neuronpedia

    INDEX
    Explanations

    snippets of code and the word "supra shoes"

    oai_token-act-pair · gemini-2.0-flash

    shoes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     just
    -0.50
     is
    -0.46
    ,
    -0.45
     have
    -0.45
     a
    -0.43
     bet
    -0.42
     you
    -0.41
     generally
    -0.40
     in
    -0.40
     has
    -0.40
    POSITIVE LOGITS
    UserScript
    1.09
     kasarigan
    1.00
    TagMode
    0.98
     onCreateView
    0.91
    setVerticalGroup
    0.89
    endphp
    0.87
     disambiguazione
    0.87
    queryInterface
    0.87
    RegressionTest
    0.86
    StoryboardSegue
    0.85
    Act Density 36.947%

    No Known Activations