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

    Neuronpedia

    INDEX
    Explanations

    Math calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     માર્ક
    -0.08
     मार्क
    -0.08
     oedd
    -0.07
    .Mark
    -0.07
    .Active
    -0.07
     మార్క
    -0.07
     యొక్క
    -0.07
     doek
    -0.07
     superfic
    -0.07
    egenomen
    -0.07
    POSITIVE LOGITS
    ,-↵↵
    0.08
     contribuer
    0.08
    ocat
    0.08
    ,-↵
    0.08
     *↵↵
    0.08
     Kläger
    0.08
    �↵↵
    0.08
    avera
    0.08
    ര
    0.08
     tambahan
    0.07
    Act Density 0.014%

    No Known Activations