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

    Neuronpedia

    INDEX
    Explanations

    references to the term "plain"

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

    plain modifier for specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ragamo
    -0.63
     queſta
    -0.60
    berdayakan
    -0.60
     PeEnEo
    -0.59
    writeFieldEnd
    -0.59
     Humber
    -0.59
    orsese
    -0.57
    featureID
    -0.57
     Mercure
    -0.57
     hashCode
    -0.56
    POSITIVE LOGITS
     plain
    2.27
     Plain
    2.19
    Plain
    2.13
    plain
    1.99
    PLAIN
    1.44
     plainly
    1.29
     plaine
    1.21
     plains
    1.07
     plaintext
    0.91
    PlainText
    0.90
    Act Density 0.011%

    No Known Activations