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

    Neuronpedia

    INDEX
    Explanations

    code-related structure and programming constructs

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

    "ID" or tokens followed by "ID"

    np_acts-logits-general · gemini-2.0-flash

    menu and identifiable IDs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Minerva
    -0.67
     Kuma
    -0.65
     Cromwell
    -0.64
     Vege
    -0.63
    期刊论文
    -0.62
     Snell
    -0.61
     Kepler
    -0.60
     Pula
    -0.58
     Strawberry
    -0.58
     Bacchus
    -0.58
    POSITIVE LOGITS
     ID
    1.73
    ID
    1.48
     setId
    1.36
     Id
    1.35
     Sid
    1.35
     getId
    1.28
    Id
    1.26
    Sid
    1.26
     IDs
    1.25
    setId
    1.23
    Act Density 0.254%

    No Known Activations