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

    Neuronpedia

    INDEX
    Explanations

    references to time, duration, and measurement data

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

    Numeric ranges

    np_acts-logits-general · gemini-2.0-flash

    number ranges, prices, or temperatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IGraphics
    -0.57
    zus
    -0.54
     تا
    -0.48
    erunner
    -0.45
    到了
    -0.45
    inheritDoc
    -0.45
    StringTo
    -0.45
     pageContext
    -0.44
    –
    -0.44
    anek
    -0.44
    POSITIVE LOGITS
     inclusive
    1.31
    inclusive
    1.28
     arasında
    1.08
     között
    1.06
     Inclusive
    1.02
     гг
    0.96
    Inclusive
    0.95
    不等
    0.93
    にかけて
    0.92
    depending
    0.91
    Act Density 0.610%

    No Known Activations