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

    Neuronpedia

    INDEX
    Explanations

    programmatic terms associated with configuration and scheduling tasks

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

    all test cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yelidikan
    -0.29
    قرار
    -0.28
     conseillers
    -0.25
    ington
    -0.24
    ,
    -0.24
     arkas
    -0.23
    TagHelper
    -0.23
    is
    -0.22
    .
    -0.22
     ratio
    -0.22
    POSITIVE LOGITS
     queſta
    0.81
     surla
    0.81
     snippetHide
    0.79
     дописавши
    0.75
    BibitemShut
    0.73
     tartalomajánló
    0.73
    saraba
    0.72
    GEBURTSDATUM
    0.71
    <unused41>
    0.71
    <pad>
    0.70
    Act Density 0.148%

    No Known Activations