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

    Neuronpedia

    INDEX
    Explanations

    concepts related to user interaction and performance in technology or device contexts

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

    user experience and function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.66
     estekak
    -0.58
    SourceChecksum
    -0.56
     
    -0.53
    RegistryLite
    -0.52
     AssemblyVersion
    -0.52
    RegressionTest
    -0.50
    apimachinery
    -0.50
     חיצוניים
    -0.48
    RuleContext
    -0.48
    POSITIVE LOGITS
     curta
    0.44
     spatial
    0.41
     feeling
    0.40
     assist
    0.40
     Assistant
    0.39
    folger
    0.39
     cognitive
    0.39
     asist
    0.39
     novel
    0.39
     user
    0.38
    Act Density 0.052%

    No Known Activations