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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal classifications and determinations

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

    deemed or considered followed by a predicate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expliquer
    -0.38
     v
    -0.32
     beautifully
    -0.32
     zugesch
    -0.32
     içeri
    -0.31
     house
    -0.30
    explique
    -0.30
     sectores
    -0.30
     yet
    -0.29
     vor
    -0.29
    POSITIVE LOGITS
     estekak
    0.78
    Tikang
    0.73
     EconPapers
    0.72
    StructEnd
    0.66
    OGND
    0.66
    parsedMessage
    0.66
    دانشنامهٔ
    0.64
     kasarigan
    0.64
     незавершена
    0.63
     ویکی‌پدی
    0.63
    Act Density 0.072%

    No Known Activations