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

    Neuronpedia

    INDEX
    Explanations

    sections or references related to discussions and analyses in research papers

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

    results and discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.68
     queſta
    -0.65
     protoimpl
    -0.65
    GEBURTSDATUM
    -0.63
    XmlAccessType
    -0.63
    AndEndTag
    -0.61
    quelize
    -0.61
     ProtoMessage
    -0.59
    IUrlHelper
    -0.58
     surla
    -0.57
    POSITIVE LOGITS
     discussion
    0.75
    Discussion
    0.72
     Discussion
    0.67
     discussed
    0.66
     discussions
    0.65
     discusses
    0.65
     discuss
    0.65
     discussão
    0.64
     discussing
    0.62
     discusión
    0.61
    Act Density 0.041%

    No Known Activations