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

    Neuronpedia

    INDEX
    Explanations

    different color references and their descriptions

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

    colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.70
    StoryboardSegue
    -0.70
    SharedDtor
    -0.65
    Cyfarwyddwr
    -0.60
    TagMode
    -0.60
     endblock
    -0.58
     nahilalakip
    -0.58
    <unused14>
    -0.58
    <unused8>
    -0.58
    <pad>
    -0.57
    POSITIVE LOGITS
     white
    0.66
     purple
    0.65
     black
    0.65
     Black
    0.63
    white
    0.62
    Black
    0.62
    gray
    0.61
     grey
    0.61
     color
    0.60
    black
    0.60
    Act Density 0.169%

    No Known Activations