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

    Neuronpedia

    INDEX
    Explanations

    common phrases related to writing and presenting information

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

    write, consider, distinguish, follow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     peines
    -0.35
    ToAction
    -0.29
     ActionResult
    -0.29
    EditorGUILayout
    -0.28
     Payne
    -0.28
    SourceType
    -0.26
    MainPage
    -0.26
     entret
    -0.26
    EntryPoint
    -0.25
     HttpContext
    -0.25
    POSITIVE LOGITS
     EconPapers
    0.73
     betweenstory
    0.67
    ंदीखरीदारी
    0.67
    :✨
    0.66
     propOrder
    0.65
     ModelExpression
    0.63
    idlertid
    0.62
     surla
    0.61
     ProtoMessage
    0.60
    SharedDtor
    0.60
    Act Density 0.349%

    No Known Activations