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

    Neuronpedia

    INDEX
    Explanations

    concepts related to optimization and efficiency

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

    ending in "ize", "ise", "ization", "isation"

    np_acts-logits-general · gemini-2.0-flash

    words ending in ize or ization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.62
    /******/
    -0.60
    
    -0.58
    Халык
    -0.57
    EndGlobalSection
    -0.56
    Билгалдахарш
    -0.54
     Merritt
    -0.53
     mergeFrom
    -0.53
    <<(
    -0.51
    sidemargin
    -0.51
    POSITIVE LOGITS
    ization
    1.32
    ized
    1.29
    izing
    1.28
    izes
    1.12
    isation
    1.10
    izations
    1.08
    ize
    1.07
    izers
    1.07
    izer
    1.05
    化
    1.01
    Act Density 0.331%

    No Known Activations