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

    Neuronpedia

    INDEX
    Explanations

    legal definitions and terms related to citizenship and nationality laws

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

    Text within parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    legal statutes and regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    centered
    -0.59
     FAVOR
    -0.59
     Center
    -0.59
     favors
    -0.58
     prioritize
    -0.58
    Centered
    -0.57
     center
    -0.56
     favor
    -0.56
     favorites
    -0.53
     favorite
    -0.53
    POSITIVE LOGITS
    RectangleBorder
    0.79
     whoſe
    0.74
    MLLoader
    0.73
     authorised
    0.71
     avoient
    0.71
     étoient
    0.70
    0.70
     enquiries
    0.70
     fubject
    0.69
    Enquiries
    0.69
    Act Density 0.316%

    No Known Activations