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

    Neuronpedia

    INDEX
    Explanations

    references to policies, rules, and regulations

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

    enacting or enforcing rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.57
    PreferredItem
    -0.54
    WriteTagHelper
    -0.48
     ModelExpression
    -0.48
    Personensuche
    -0.44
    cửa
    -0.44
    ScopeManager
    -0.43
     NgModule
    -0.43
     CURIAM
    -0.43
    SourceChecksum
    -0.43
    POSITIVE LOGITS
     strict
    0.43
     restri
    0.43
     ped
    0.42
     stricter
    0.42
     enforce
    0.38
     report
    0.38
     tighten
    0.38
     loo
    0.36
     rul
    0.36
     law
    0.36
    Act Density 0.049%

    No Known Activations