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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific formatting characters, likely indicating sections, end statements, or notes of significance

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

    LaTeX and Markdown citations/references

    np_acts-logits-general · gemini-2.0-flash

    citation markers and section breaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FailureListener
    -0.53
    ^
    -0.47
     Dickson
    -0.47
     gốc
    -0.45
    falen
    -0.44
    TagHelper
    -0.44
     للاسماء
    -0.44
     die
    -0.44
     Pe
    -0.44
    askar
    -0.44
    POSITIVE LOGITS
    subsubsection
    1.25
    subsection
    1.03
     estekak
    0.69
    weile
    0.63
     CHAPITRE
    0.62
     CHAPTER
    0.60
    SharedCtor
    0.58
    awaiter
    0.57
    ]")]
    0.57
    didSet
    0.56
    Act Density 0.062%

    No Known Activations