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

    Neuronpedia

    INDEX
    Explanations

    references to entities and their relationships in a structured data format

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

    entity and its manager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     democrática
    -0.49
     automático
    -0.47
    ImageContext
    -0.43
     esquerdo
    -0.40
     izquierdo
    -0.40
     useAppContext
    -0.40
    Попис
    -0.40
     måte
    -0.39
     mecánico
    -0.39
    用水
    -0.39
    POSITIVE LOGITS
     entity
    1.30
     Entity
    1.17
     entities
    1.13
    实体
    1.08
    entity
    1.08
     ENTITY
    1.06
    Entity
    1.05
     Entities
    1.04
    ENTITY
    1.02
    getEntity
    0.96
    Act Density 0.011%

    No Known Activations