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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships among elements in technical or procedural contexts

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

    preceding "and", "or", and "the"

    np_acts-logits-general · gemini-2.0-flash

    or endings, distal, reverse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Utara
    -0.67
     utara
    -0.59
    ">+
    -0.56
     north
    -0.55
     上午
    -0.53
    ]>=
    -0.53
    northern
    -0.53
     canadienne
    -0.53
     Serikat
    -0.52
     africaine
    -0.51
    POSITIVE LOGITS
    setVerticalGroup
    1.12
    AccessorTable
    0.95
     oprot
    0.86
    StructEnd
    0.82
    endregion
    0.74
    EndContext
    0.73
     GenerationType
    0.70
     postIndex
    0.68
     pinulongan
    0.65
    PostInfinity
    0.65
    Act Density 0.667%

    No Known Activations