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

    Neuronpedia

    INDEX
    Explanations

    API requests and methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boy
    -0.08
     extensions
    -0.08
     Winston
    -0.07
     HOL
    -0.07
     longevity
    -0.07
     boys
    -0.07
    保证
    -0.07
     holiness
    -0.07
     cruis
    -0.07
     Tus
    -0.07
    POSITIVE LOGITS
    sebenzi
    0.08
    hetho
    0.08
    684
    0.08
    物
    0.08
    .perform
    0.08
     ejec
    0.08
     выполнения
    0.08
     interpreta
    0.08
     Discovery
    0.08
     Executes
    0.07
    Act Density 0.001%

    No Known Activations