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

    Neuronpedia

    INDEX
    Explanations

    conditions and variables that affect outcomes or measurements

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

    depending on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ciudadana
    -0.41
     kvä
    -0.40
     terecht
    -0.40
     totalité
    -0.37
     zpě
    -0.36
    녕
    -0.36
     tilbake
    -0.35
     võimal
    -0.35
     balik
    -0.35
     defaultstate
    -0.35
    POSITIVE LOGITS
    Portail
    0.73
    sizeCache
    0.59
     AssemblyCompany
    0.57
    يكب
    0.54
    ValueGeneration
    0.54
     propOrder
    0.53
    RuleContext
    0.52
    تقاوى
    0.52
    tagHelper
    0.51
    InvalidProtocol
    0.51
    Act Density 0.020%

    No Known Activations