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

    Neuronpedia

    INDEX
    Explanations

    key facts or data points within technical or formal documents

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

    without opposed can unfortunately if resistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.84
     estekak
    -0.82
     ujednoznacz
    -0.71
     disambiguazione
    -0.71
    tvguidetime
    -0.68
     gynhyrchwyd
    -0.67
     propOrder
    -0.66
     Administrativna
    -0.66
     パンチラ
    -0.63
    <unused14>
    -0.62
    POSITIVE LOGITS
    princip
    0.29
    where
    0.28
    ╚
    0.27
    ValueStyle
    0.27
    fd
    0.26
    so
    0.26
    にあります
    0.26
    num
    0.26
    qu
    0.26
    tagHelper
    0.26
    Act Density 0.071%

    No Known Activations