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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and relationships related to energy density and conditions

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

    Mathematical or scientific comparisons/inequalities

    np_acts-logits-general · gemini-2.0-flash

    comparisons with thresholds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moins
    -1.11
     smaller
    -1.04
     Less
    -1.04
     Smaller
    -1.01
    Less
    -1.01
     less
    -1.01
     lowest
    -0.99
    smaller
    -0.99
    lowest
    -0.98
    moins
    -0.98
    POSITIVE LOGITS
     >
    1.15
     (>
    1.00
     }>
    0.99
     $>
    0.97
     }}>
    0.96
    >
    0.96
    }>
    0.95
     >=
    0.93
     above
    0.90
    ]>
    0.90
    Act Density 0.739%

    No Known Activations