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

    Neuronpedia

    INDEX
    Explanations

    structured data or code-related elements in documents

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

    after "all", "give", "than", or "resp"

    np_acts-logits-general · gemini-2.0-flash

    both/either duality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GetEnumerator
    -0.56
     groupBox
    -0.52
     kasarigan
    -0.51
    MenuInflater
    -0.50
     estimés
    -0.49
     ProtoMessage
    -0.48
     ModelExpression
    -0.46
    liothèque
    -0.44
    dientemente
    -0.44
    OGND
    -0.44
    POSITIVE LOGITS
     both
    1.34
    both
    1.26
     både
    1.20
    Both
    1.17
     zowel
    1.12
     Both
    1.10
     sowohl
    1.08
     zarówno
    1.05
     BOTH
    1.00
    ทั้ง
    0.95
    Act Density 0.994%

    No Known Activations