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

    Neuronpedia

    INDEX
    Explanations

    references to color codes or attributes in a programming context

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

    color codes and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.73
     wireType
    -0.63
    ſelves
    -0.58
    uarine
    -0.58
    ágenes
    -0.56
    RegistryLite
    -0.55
    ividual
    -0.55
    至於
    -0.54
    farwydd
    -0.54
     indígen
    -0.54
    POSITIVE LOGITS
    color
    2.22
    COLOR
    1.27
    Color
    1.13
    colour
    1.03
     Color
    0.96
     COLOR
    0.91
    colors
    0.89
     color
    0.88
    colore
    0.86
    olor
    0.83
    Act Density 0.004%

    No Known Activations