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

    Neuronpedia

    INDEX
    Explanations

    references to memory addresses and pointer-related syntax in code

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

    C++ code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.75
     MenuView
    -0.65
    uxxxx
    -0.61
    antası
    -0.57
     Catawiki
    -0.57
     unknownFields
    -0.56
    Erstellt
    -0.55
     EconPapers
    -0.54
     Signalez
    -0.54
    enderror
    -0.54
    POSITIVE LOGITS
    setof
    0.51
    (&(
    0.49
     *)&
    0.49
    sizeof
    0.48
    nameof
    0.45
    (&
    0.45
     sizeof
    0.45
     nameof
    0.42
    offsetof
    0.40
    ((&
    0.36
    Act Density 0.121%

    No Known Activations