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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional sentiments and social reflections

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

    followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    abilities, attention, preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ără
    -0.46
     nélk
    -0.46
    side
    -0.43
     Found
    -0.43
    Found
    -0.42
     образования
    -0.41
    води
    -0.41
    Hughes
    -0.40
    pení
    -0.40
    ]<<"
    -0.40
    POSITIVE LOGITS
     ModelExpression
    0.83
     propOrder
    0.78
     AssemblyCulture
    0.78
    RectangleBorder
    0.74
     <=",
    0.73
    WriteBarrier
    0.73
     متعلقه
    0.72
     XCTest
    0.72
    helves
    0.71
    NewUrlParser
    0.69
    Act Density 0.438%

    No Known Activations