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

    Neuronpedia

    INDEX
    Explanations

    references to communities and community members

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

    community edition, license, members, effort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.58
     ſmall
    -0.52
     '\\;'
    -0.52
     faſt
    -0.50
    Климат
    -0.48
    WriteTagHelper
    -0.47
     Monfieur
    -0.46
     deſt
    -0.46
     leſs
    -0.44
     ſind
    -0.44
    POSITIVE LOGITS
     community
    1.10
    Community
    1.10
    community
    1.09
     COMMUNITY
    1.05
     Community
    1.02
    COMMUNITY
    0.97
     komunitas
    0.97
     comunidade
    0.90
     comunidad
    0.89
     communities
    0.82
    Act Density 0.009%

    No Known Activations