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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fabric
    -0.08
    :px
    -0.08
    .private
    -0.08
     vid
    -0.07
    淘
    -0.07
    舍
    -0.07
    부터
    -0.07
     disagree
    -0.07
    锐
    -0.07
     Richter
    -0.07
    POSITIVE LOGITS
     keywords
    0.10
     keyword
    0.10
    Keyword
    0.09
     Keyword
    0.09
    Keywords
    0.09
     Keywords
    0.09
    _keyword
    0.09
    关键词
    0.08
    _keywords
    0.08
     mencionar
    0.08
    Act Density 0.015%

    No Known Activations