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

    Neuronpedia

    INDEX
    Explanations

    negative indicators of quantitative values or statistics

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

    numbers written as words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.63
    Gaia
    -0.56
    ◀
    -0.53
    $_['
    -0.52
    PYX
    -0.52
     coerci
    -0.52
     Gaia
    -0.51
     Amazonas
    -0.51
    URLException
    -0.50
    tsun
    -0.50
    POSITIVE LOGITS
     ninety
    0.57
     twenty
    0.55
     seventy
    0.54
     forty
    0.49
     thirty
    0.49
     nineteenth
    0.49
     seventeenth
    0.48
     sixty
    0.47
     Ninety
    0.47
    étoit
    0.47
    Act Density 0.007%

    No Known Activations