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

    Neuronpedia

    INDEX
    Explanations

    variables or parameters related to configuration or state in a coding context

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

    small numbers, zero padding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wikipagina
    -0.68
     löyty
    -0.60
    往下閱讀
    -0.59
    wiliwch
    -0.59
     CreateTagHelper
    -0.58
     doświad
    -0.57
     dilengkapi
    -0.57
     tarvit
    -0.57
    iſchen
    -0.57
     calitate
    -0.56
    POSITIVE LOGITS
    0
    0.43
    ########.
    0.38
    FFFF
    0.35
    oooo
    0.34
    ooo
    0.34
     aaa
    0.33
     Mary
    0.32
     Yamato
    0.31
    haha
    0.31
    zzz
    0.31
    Act Density 0.055%

    No Known Activations