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

    Neuronpedia

    INDEX
    Explanations

    references to filtering documents or data in programming contexts

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

    property, module, and connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.68
     CreateTagHelper
    -0.57
     EconPapers
    -0.54
     Taktlose
    -0.48
    balleur
    -0.47
     CURLOPT
    -0.45
    basicConfig
    -0.45
     CanadaChoose
    -0.45
    BufferException
    -0.44
    ImageContext
    -0.44
    POSITIVE LOGITS
     val
    0.50
    val
    0.46
     Val
    0.43
     draw
    0.41
     plan
    0.40
     run
    0.40
     bag
    0.40
    Aiheesta
    0.40
     kemungkinan
    0.39
     simultaneously
    0.39
    Act Density 0.023%

    No Known Activations