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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and expressions in various forms

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

    Fractions and sequences

    np_acts-logits-general · gemini-2.0-flash

    ordinal numbers twelve and thirteen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IRST
    -0.57
    mers
    -0.52
    quiera
    -0.52
     ONE
    -0.51
    impl
    -0.49
    ignty
    -0.48
     FIRST
    -0.47
    One
    -0.46
     One
    -0.46
     vuông
    -0.45
    POSITIVE LOGITS
     thirteenth
    0.90
     twelfth
    0.89
     Thirteen
    0.87
     Twelve
    0.83
     Thirteenth
    0.82
    Thirteen
    0.82
     Fourteenth
    0.81
    Twelve
    0.81
     fourteenth
    0.80
     twelve
    0.80
    Act Density 0.515%

    No Known Activations