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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface components in code

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

    html tag names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.78
     ſind
    -0.77
     المعيارى
    -0.70
    InSection
    -0.68
     MainAxisSize
    -0.67
     للمعارف
    -0.67
     <=",
    -0.67
    存于互联网档案馆
    -0.65
     ſein
    -0.65
    jsxFileName
    -0.64
    POSITIVE LOGITS
    ↵↵
    0.71
    ↵↵↵
    0.69
    ↵↵↵↵
    0.64
    ↵↵↵↵↵↵
    0.57
    ↵↵↵↵↵
    0.56
    ↵↵↵↵↵↵↵
    0.56
    ↵↵↵↵↵↵↵↵↵
    0.53
    <eos>
    0.50
    ↵↵↵↵↵↵↵↵
    0.49
    ↵
    0.49
    Act Density 0.019%

    No Known Activations