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

    Neuronpedia

    INDEX
    Explanations

    references to color, specifically shades of blue and gray

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

    associated with colors

    np_acts-logits-general · gemini-2.0-flash

    blue, grey, yellow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.98
     Normdatei
    -0.91
     ComVisible
    -0.87
    ArgsConstructor
    -0.81
    ContentAsync
    -0.74
     protoimpl
    -0.72
     ainfi
    -0.72
     hâte
    -0.71
    Vidite
    -0.69
     propOrder
    -0.69
    POSITIVE LOGITS
     colored
    0.59
     haired
    0.58
     matter
    0.51
    haired
    0.50
     skinned
    0.50
    washing
    0.50
     coloured
    0.50
     smoke
    0.48
    wash
    0.48
    colored
    0.47
    Act Density 0.150%

    No Known Activations