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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctive phrases

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

    list of colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.68
    NameInMap
    -0.66
     Roskov
    -0.64
    principalColumn
    -0.64
    MLLoader
    -0.61
    liceerd
    -0.60
    PARATUS
    -0.59
    Rhestr
    -0.59
    TagMode
    -0.59
    zzleHttp
    -0.59
    POSITIVE LOGITS
     color
    1.00
     colors
    0.89
     colour
    0.86
     Color
    0.85
     COLOR
    0.81
    Color
    0.79
     blue
    0.78
     colours
    0.77
     Colors
    0.75
     red
    0.72
    Act Density 0.055%

    No Known Activations