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

    Neuronpedia

    INDEX
    Explanations

    uses of the word "not" or the contraction "isn't".

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'least'

    np_token-act-pair-logits · gpt-4o-mini

    Negative sentiment/reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.85
    tagext
    -0.79
    はじめに
    -0.75
    HandlerContext
    -0.72
     &___
    -0.65
    withIdentifier
    -0.65
    sizeCache
    -0.65
    addPreferredGap
    -0.63
     RequestMethod
    -0.63
    CompilerServices
    -0.63
    POSITIVE LOGITS
     Factbook
    0.42
     least
    0.42
    least
    0.41
    нинград
    0.41
    VARI
    0.41
     Legacy
    0.41
    Least
    0.40
    ValueStyle
    0.40
    Fiche
    0.40
     ули
    0.40
    Act Density 0.622%

    No Known Activations