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

    Neuronpedia

    INDEX
    Explanations

    specific statistical metrics related to demographics or health

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

    numbers followed by percent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.41
     kasarigan
    -0.38
    Resume
    -0.36
    <eos>
    -0.35
     despite
    -0.34
    zulegen
    -0.34
     Bar
    -0.34
     without
    -0.34
    B
    -0.34
     while
    -0.33
    POSITIVE LOGITS
    BufferException
    0.70
     ویکی‌پدیا
    0.66
    RegressionTest
    0.66
     ſind
    0.66
     Normdatei
    0.65
     MainAxisSize
    0.63
     препратки
    0.62
    Datuak
    0.62
    AndEndTag
    0.60
    InjectAttribute
    0.60
    Act Density 0.436%

    No Known Activations