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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation or expressions

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

    Numbers used as exponents or powers

    np_acts-logits-general · gemini-2.0-flash

    numbers after a count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sixty
    -1.07
     Sixty
    -1.06
     eighty
    -1.02
     Fifty
    -1.02
     Eighty
    -1.01
     seventy
    -1.00
     Seventy
    -1.00
     Thirty
    -0.99
     ninety
    -0.98
     fifty
    -0.97
    POSITIVE LOGITS
     two
    1.01
     deux
    0.96
    two
    0.90
     zwei
    0.83
     TWO
    0.81
    2
    0.77
    Two
    0.76
    TWO
    0.75
     dois
    0.74
     Two
    0.73
    Act Density 1.785%

    No Known Activations