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

    Neuronpedia

    INDEX
    Explanations

    references to figures and tables in a document

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

    references to figures and tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.64
     informée
    -0.64
    Personensuche
    -0.63
    InputTagHelper
    -0.62
    AccessorTable
    -0.58
     gyhoeddwyd
    -0.57
     dAtA
    -0.56
     فريبيس
    -0.55
    :✨
    -0.54
    ftagPool
    -0.53
    POSITIVE LOGITS
    出版年
    0.35
     ✭✭
    0.35
    FOLK
    0.30
     betweenstory
    0.30
    styleType
    0.28
     cláus
    0.26
    Makefile
    0.26
     contado
    0.25
    basicConfig
    0.25
    trường
    0.24
    Act Density 0.140%

    No Known Activations