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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to serialization and memory structures

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

    ending in "-al," "-ial," "-il," or "-ent"

    np_acts-logits-general · gemini-2.0-flash

    words ending in -al followed by -ize/-ization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.69
    IntoConstraints
    -0.66
    
    -0.64
     Italijani
    -0.57
    WebElementEntity
    -0.57
     שוליים
    -0.57
     Paglinawan
    -0.56
    ValueStyle
    -0.52
    windowFixed
    -0.51
     InputDecoration
    -0.50
    POSITIVE LOGITS
    ized
    2.45
    ization
    2.27
    izing
    2.11
    ize
    1.98
    isation
    1.92
    ised
    1.85
    izes
    1.81
    izations
    1.78
    istic
    1.77
    ists
    1.64
    Act Density 0.797%

    No Known Activations