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

    Neuronpedia

    INDEX
    Explanations

    programming-related definitions and function declarations

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

    macros and constants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -1.00
     للاسماء
    -0.92
     disambiguazione
    -0.90
    parsedMessage
    -0.88
     パンチラ
    -0.86
    niſſe
    -0.86
    <unused41>
    -0.86
    <unused17>
    -0.86
    <unused16>
    -0.86
    <pad>
    -0.86
    POSITIVE LOGITS
    1
    0.51
    2
    0.50
    3
    0.45
    0
    0.44
    9
    0.44
    4
    0.43
    5
    0.43
     but
    0.42
    7
    0.41
    ↵↵↵
    0.40
    Act Density 0.023%

    No Known Activations