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

    Neuronpedia

    INDEX
    Explanations

    Standard English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Maven
    -0.06
     shortcomings
    -0.06
     greet
    -0.06
     damaging
    -0.06
     disposing
    -0.06
     Humans
    -0.06
     basePath
    -0.06
     MyBase
    -0.06
     Winds
    -0.06
     warranted
    -0.06
    POSITIVE LOGITS
     itemprop
    0.07
    =".$
    0.06
     rowNum
    0.06
    !,↵
    0.06
    /
    0.06
    investment
    0.06
    _FD
    0.06
    だけ
    0.06
     منت
    0.06
    >R
    0.06
    Act Density 0.065%

    No Known Activations