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

    Neuronpedia

    INDEX
    Explanations

    instances of observation and awareness

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

    comes or goes back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     presentaron
    -0.34
     Werken
    -0.33
     бути
    -0.33
     Geller
    -0.33
     Burk
    -0.32
    FORMANCE
    -0.31
    ToBe
    -0.31
     aplican
    -0.31
    ieder
    -0.31
     libéral
    -0.31
    POSITIVE LOGITS
     EconPapers
    0.75
    IsContent
    0.72
     дописавши
    0.61
     مرئيه
    0.61
    transQ
    0.60
     queſta
    0.58
    RegressionTest
    0.57
     IndexPath
    0.54
    PreferredItem
    0.53
     betweenstory
    0.53
    Act Density 0.059%

    No Known Activations