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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and numerical values in a scientific context

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

    Exponents or powers of ten

    np_acts-logits-general · gemini-2.0-flash

    scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    наче
    -0.48
    帖最后由
    -0.47
     Audiodateien
    -0.45
     Claro
    -0.43
    ‍♂️
    -0.42
    temon
    -0.42
     })}
    -0.41
    €¢
    -0.41
    bez
    -0.40
    roek
    -0.40
    POSITIVE LOGITS
    <sup>
    1.35
    ^{
    1.18
    ^
    1.18
     ^
    1.06
    ^(
    1.01
    $^{
    1.00
     ^{
    0.98
    ^[
    0.91
     ${
    0.91
     $^{
    0.87
    Act Density 1.665%

    No Known Activations