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

    Neuronpedia

    INDEX
    Explanations

    patterns of punctuation and imports in code snippets

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

    start of turn,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erati
    -0.32
     сро
    -0.32
    hela
    -0.30
    ﴿
    -0.30
     report
    -0.30
     fraction
    -0.29
    filepath
    -0.29
     mysqli
    -0.28
    php
    -0.28
    aratus
    -0.28
    POSITIVE LOGITS
     otomatig
    0.62
    ::*;
    0.60
     виправивши
    0.60
     propOrder
    0.59
    الحياه
    0.56
     disambiguazione
    0.55
    setof
    0.54
    dAtA
    0.54
    CloseOperation
    0.54
     unſer
    0.54
    Act Density 0.007%

    No Known Activations