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

    Neuronpedia

    INDEX
    Explanations

    hierarchical data structures or ranges associated with parameters and settings

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

    high quality, performance, or level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.62
    ensory
    -0.53
    zám
    -0.50
     yyr
    -0.50
    principalColumn
    -0.47
    理石
    -0.47
    SqlClient
    -0.45
    WriteBarrier
    -0.45
     Benzene
    -0.44
    ConverterFactory
    -0.43
    POSITIVE LOGITS
     high
    1.02
     High
    0.95
    high
    0.92
    High
    0.90
     low
    0.85
     Low
    0.82
    Low
    0.75
    HIGH
    0.74
     HIGH
    0.73
     عالية
    0.68
    Act Density 0.333%

    No Known Activations