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

    Neuronpedia

    INDEX
    Explanations

    references to colors and their usage in graphical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Colors

    np_acts-logits-general · gemini-2.0-flash

    colors in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.53
    dbh
    -0.49
    íncipe
    -0.47
    adhi
    -0.46
     AssemblyVersion
    -0.45
     diting
    -0.41
     AspNetCore
    -0.41
     lavoratori
    -0.41
    धि
    -0.41
    リート
    -0.40
    POSITIVE LOGITS
     green
    1.60
     yellow
    1.55
     purple
    1.54
     blue
    1.54
     pink
    1.42
     orange
    1.42
     red
    1.38
    green
    1.33
    blue
    1.28
    yellow
    1.26
    Act Density 0.227%

    No Known Activations