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

    Neuronpedia

    INDEX
    Explanations

    numerical data or references related to experimental results

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

    citations in academic texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.49
    localctx
    -0.42
    TemporalType
    -0.41
    IndentedString
    -0.41
     démocratique
    -0.41
    WebElementEntity
    -0.39
    fromLTRB
    -0.39
     democrá
    -0.38
     שוליים
    -0.36
     armar
    -0.36
    POSITIVE LOGITS
     ſta
    0.62
     myſelf
    0.54
     raiſ
    0.53
     himſelf
    0.49
     againſt
    0.48
     ſever
    0.47
     pleaſure
    0.46
     inſ
    0.46
    ticides
    0.45
     ſaid
    0.45
    Act Density 0.046%

    No Known Activations