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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data or statistics

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

    Numbers or numerical ranges

    np_acts-logits-general · gemini-2.0-flash

    ordinal numbers 8-12

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    -0.60
     ২
    -0.52
     ostavi
    -0.47
     Twenty
    -0.47
    DispatchToProps
    -0.45
    IANGLES
    -0.45
     trent
    -0.43
    Twenty
    -0.43
    EDEFAULT
    -0.42
    เส
    -0.42
    POSITIVE LOGITS
     ninth
    0.97
     nine
    0.92
     eleventh
    0.92
     twelfth
    0.90
    Eleven
    0.90
     Eleventh
    0.90
     eighth
    0.89
     Ninth
    0.89
     tenth
    0.87
     Eleven
    0.86
    Act Density 0.658%

    No Known Activations