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

    Neuronpedia

    INDEX
    Explanations

    non-verbal elements, such as punctuation or spacing in the text

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

    math problems and calculations

    np_acts-logits-general · gemini-2.0-flash

    math and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    APPENDICES
    -0.52
     fully
    -0.45
     brazos
    -0.41
     —
    -0.41
     destin
    -0.40
     pilares
    -0.39
     kval
    -0.39
     sumber
    -0.39
    princip
    -0.39
    Appendices
    -0.39
    POSITIVE LOGITS
    TagMode
    0.97
     NSCoder
    0.91
    MessageTagHelper
    0.89
     InputDecoration
    0.86
    RegressionTest
    0.79
    DockStyle
    0.76
    tagHelperRunner
    0.75
     questions
    0.75
     riddle
    0.75
     question
    0.74
    Act Density 0.301%

    No Known Activations