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

    Neuronpedia

    INDEX
    Explanations

    instances of structured data or programming logic

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

    legal institutional understanding follow store

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.88
     referrerpolicy
    -0.86
    protoimpl
    -0.85
     المعيارى
    -0.85
    MessageTagHelper
    -0.82
     Wikimedijinoj
    -0.81
     للاسماء
    -0.80
    awtextra
    -0.79
     TextAlign
    -0.78
     snippetHide
    -0.78
    POSITIVE LOGITS
     Legal
    0.37
     legal
    0.36
    Institutional
    0.35
     Institutional
    0.35
     Understanding
    0.35
     Bruder
    0.34
     Institution
    0.33
     follow
    0.33
     store
    0.33
     들어
    0.33
    Act Density 0.001%

    No Known Activations