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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the results of studies or research findings

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

    shown to or that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.59
     Stray
    -0.51
    ंदीखरीदारी
    -0.50
     EconPapers
    -0.48
     propOrder
    -0.48
    NameInMap
    -0.48
     سكانية
    -0.43
     Perf
    -0.42
     Decoration
    -0.41
    peted
    -0.41
    POSITIVE LOGITS
     effectiveness
    0.47
     effective
    0.43
    CrossRef
    0.41
     mampu
    0.40
    omock
    0.40
     positive
    0.39
     onAnimation
    0.39
     efficacious
    0.39
     terbukti
    0.38
     mempengaruhi
    0.38
    Act Density 0.111%

    No Known Activations