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

    Neuronpedia

    INDEX
    Explanations

    expressions related to performance and effectiveness

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

    performance of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atguigu
    -0.40
     kiss
    -0.36
    <h1>
    -0.36
     knot
    -0.35
     necessários
    -0.35
     gas
    -0.35
    sendFile
    -0.35
     gift
    -0.34
    uus
    -0.34
    FileDialog
    -0.32
    POSITIVE LOGITS
     performance
    1.19
    performance
    1.08
     performances
    1.03
    PERFORMANCE
    1.02
     Performance
    1.01
     PERFORMANCE
    1.00
    Performance
    0.99
     desempenho
    0.89
     Performances
    0.87
    Performances
    0.83
    Act Density 0.028%

    No Known Activations