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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "ten" or variations of the word in contexts outside standard meaning

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

    Numbers, especially "0" and "ten"

    np_acts-logits-general · gemini-2.0-flash

    ten, 0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مُعرِّف
    -0.66
     nahilalakip
    -0.61
    elemField
    -0.56
    ScopeManager
    -0.56
    ituaries
    -0.54
     sort
    -0.53
    SpringBootTest
    -0.53
    subsubsection
    -0.51
    GeneratedCode
    -0.51
    icolon
    -0.50
    POSITIVE LOGITS
    0
    1.00
     invokingState
    0.85
     Downing
    0.75
     Commandments
    0.73
    AddTagHelper
    0.68
     commandments
    0.67
    AndEndTag
    0.61
    8
    0.60
     Tors
    0.60
    ^{-
    0.60
    Act Density 0.288%

    No Known Activations