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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "raw" related to URLs or file types

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

    raw data and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BehaviorSubject
    -0.57
    tanleria
    -0.56
     مرئيه
    -0.48
    RepeatedField
    -0.48
    NameInMap
    -0.47
    RegistryLite
    -0.46
    autoreleasepool
    -0.45
     endregion
    -0.45
    <bos>
    -0.44
     $_[
    -0.44
    POSITIVE LOGITS
    raw
    3.19
     raw
    2.47
    Raw
    2.41
     Raw
    2.34
    RAW
    2.30
     RAW
    2.03
    getRaw
    1.42
    RawData
    1.28
    rawl
    1.27
    rawData
    1.27
    Act Density 0.004%

    No Known Activations