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

    Neuronpedia

    INDEX
    Explanations

    table data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    doi
    -0.07
    เทพ
    -0.06
     befind
    -0.06
    ampoo
    -0.06
     conclusion
    -0.06
    Apply
    -0.06
     doubling
    -0.06
    _Post
    -0.06
    went
    -0.06
     amen
    -0.06
    POSITIVE LOGITS
     بازی
    0.07
    (write
    0.07
     sınır
    0.07
     Aralık
    0.07
     searchText
    0.06
     uomini
    0.06
    _txt
    0.06
    .ly
    0.06
     components
    0.06
    한국
    0.06
    Act Density 0.076%

    No Known Activations