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

    Neuronpedia

    INDEX
    Explanations

    changing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _queries
    -0.07
    完整
    -0.06
     Analy
    -0.06
    Analyzer
    -0.06
    .AdapterView
    -0.06
    .fragments
    -0.06
    523
    -0.06
    eature
    -0.06
     momentum
    -0.06
    Seats
    -0.06
    POSITIVE LOGITS
     बढ़
    0.07
    одатель
    0.07
    utenant
    0.06
    perms
    0.06
     buna
    0.06
    lords
    0.06
    unitOfWork
    0.06
     refin
    0.06
    0.06
    .Child
    0.06
    Act Density 0.008%

    No Known Activations