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

    Neuronpedia

    INDEX
    Explanations

    Classes/Jobs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fraternity
    -0.07
     propertyName
    -0.07
     rethink
    -0.06
    排名
    -0.06
    يرا
    -0.06
    "bytes
    -0.06
    Severity
    -0.06
     marketed
    -0.06
     Highlights
    -0.06
    logradouro
    -0.06
    POSITIVE LOGITS
     unloaded
    0.07
    存档
    0.06
     obten
    0.06
    ibilidad
    0.06
    utenant
    0.06
     position
    0.06
    지요
    0.06
    ylie
    0.06
    enko
    0.06
    pt
    0.06
    Act Density 0.038%

    No Known Activations