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

    Neuronpedia

    INDEX
    Explanations

    numbered lists and steps

    oai_token-act-pair · gemini-2.0-flash

    one/two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.76
    rrggbb
    -0.73
     FileWriter
    -0.68
    tamount
    -0.67
     Paglinawan
    -0.67
     teapot
    -0.66
     CreateTagHelper
    -0.65
     $_"
    -0.65
    piles
    -0.63
     Paraly
    -0.63
    POSITIVE LOGITS
    <bos>
    0.66
    UnknownFieldSet
    0.47
     atsi
    0.46
     tiens
    0.46
     the
    0.45
     समीक्षाओं
    0.43
     saisir
    0.42
     disambiguazione
    0.42
     fim
    0.41
    oredCriteria
    0.41
    Act Density 5.036%

    No Known Activations