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

    Neuronpedia

    INDEX
    Explanations

    IEEE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çat
    -0.07
    (series
    -0.07
    тон
    -0.07
    _uart
    -0.06
     Prote
    -0.06
     сч
    -0.06
    -design
    -0.06
     Locke
    -0.06
    童
    -0.06
    .mapper
    -0.06
    POSITIVE LOGITS
     no
    0.07
     No
    0.07
     pretext
    0.07
    aser
    0.07
    <Type
    0.06
     seated
    0.06
     acceptable
    0.06
     전체
    0.06
       ↵↵
    0.06
    UG
    0.06
    Act Density 0.001%

    No Known Activations