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

    Neuronpedia

    INDEX
    Explanations

    high-frequency numerical sequences that could represent data points or identifiers

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

    The number 9 or related terms

    np_acts-logits-general · gemini-2.0-flash

    the number nine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noqa
    -0.73
    di
    -0.63
    一个
    -0.62
    vatel
    -0.61
    ces
    -0.61
    ertale
    -0.61
    uley
    -0.58
    ża
    -0.58
    riwal
    -0.58
    forma
    -0.58
    POSITIVE LOGITS
    9
    1.34
     NINE
    1.03
    nine
    0.99
     Ninth
    0.93
    ninth
    0.92
    ۹
    0.90
     ninety
    0.90
     nueve
    0.88
     ninth
    0.88
    jestic
    0.86
    Act Density 0.891%

    No Known Activations