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

    Neuronpedia

    INDEX
    Explanations

    legal terminology related to judicial authority and guidelines

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

    legal citations and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.76
    الإنجليزية
    -0.72
    granate
    -0.67
     Préférences
    -0.67
     indígen
    -0.63
    cerpts
    -0.63
     queſta
    -0.61
    әрмәләр
    -0.61
    -0.60
     postIndex
    -0.60
    POSITIVE LOGITS
    ↵↵↵
    0.67
    ↵↵↵↵↵
    0.56
    ↵↵↵↵
    0.54
    ↵↵↵↵↵↵
    0.47
    ↵↵↵↵↵↵↵
    0.46
    ...
    0.41
    ↵↵↵↵↵↵↵↵↵↵↵
    0.38
    ↵↵↵↵↵↵↵↵
    0.38
     ...
    0.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.37
    Act Density 0.022%

    No Known Activations