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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references in a legal or formal context

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

    Citations with numbers and symbols

    np_acts-logits-general · gemini-2.0-flash

    legal citations and case numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.36
    ivu
    -0.33
     Wednesday
    -0.32
     citi
    -0.32
     tử
    -0.31
     Polk
    -0.31
    eki
    -0.31
     Citi
    -0.31
     otomatig
    -0.31
     arr
    -0.30
    POSITIVE LOGITS
    exitRule
    0.59
     defaultstate
    0.57
     المعيارى
    0.54
     aDecoder
    0.53
    TagMode
    0.53
    findpost
    0.53
    ngrx
    0.50
    TestingModule
    0.50
     EconPapers
    0.49
    onomía
    0.49
    Act Density 0.685%

    No Known Activations