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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and syntax

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

    Changes preceded by plus or minus signs

    np_acts-logits-general · gemini-2.0-flash

    instead of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextAlign
    -0.52
    windowFixed
    -0.47
    Portale
    -0.46
     &___
    -0.45
    AccessorTable
    -0.45
     contextLoads
    -0.45
     سكانية
    -0.44
     Normdatei
    -0.44
     associative
    -0.42
    ❉
    -0.42
    POSITIVE LOGITS
    更
    0.56
     instead
    0.54
     replaced
    0.52
    Kjelder
    0.50
     istället
    0.49
     closer
    0.49
     更
    0.46
    easier
    0.45
     easier
    0.43
     Instead
    0.43
    Act Density 0.608%

    No Known Activations