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

    Neuronpedia

    INDEX
    Explanations

    high frequency terms related to statistical and analytical processes

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

    initial word of phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.49
    Obituary
    -0.45
    kloped
    -0.44
     Bod
    -0.43
     propOrder
    -0.42
    WTS
    -0.41
    LineColor
    -0.41
    <eos>
    -0.41
    liere
    -0.40
    Tk
    -0.40
    POSITIVE LOGITS
    :✨
    0.68
     kasarigan
    0.57
     perlas
    0.43
     vět
    0.42
     שוליים
    0.42
     Wiktionnaire
    0.42
    หลวง
    0.41
    windowFixed
    0.39
     lenker
    0.39
    Ҭ
    0.38
    Act Density 0.005%

    No Known Activations