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

    Neuronpedia

    INDEX
    Explanations

    terms related to datasets, variables, and experimental parameters

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

    labels in tables and datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -1.12
     للمعارف
    -1.11
    OGND
    -1.01
    principalColumn
    -1.00
    PreferredItem
    -0.80
    #+#
    -0.75
    ValueStyle
    -0.75
    LEncoder
    -0.72
    ésultats
    -0.71
     Normdatei
    -0.70
    POSITIVE LOGITS
    ,
    0.41
    :
    0.33
     Coach
    0.32
    Name
    0.32
    ↵
    0.32
     name
    0.32
     coach
    0.32
     (
    0.31
    istung
    0.31
    ksin
    0.31
    Act Density 0.030%

    No Known Activations