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

    Neuronpedia

    INDEX
    Explanations

    concepts relating to social justice and personal narratives

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

    consequence and norms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Архівовано
    -0.41
    WithIdentifier
    -0.41
    ihnachts
    -0.40
    Lịch
    -0.37
    Scha
    -0.37
    höhung
    -0.37
    ấm
    -0.36
     précise
    -0.36
    TestingModule
    -0.35
    Leer
    -0.35
    POSITIVE LOGITS
    oneofs
    0.55
    StructEnd
    0.50
     resourceCulture
    0.48
     propOrder
    0.47
    adaptiveStyles
    0.44
     StatelessWidget
    0.43
    ImageContext
    0.42
    dropbox
    0.41
     auroit
    0.41
    InjectAttribute
    0.40
    Act Density 0.050%

    No Known Activations