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

    Neuronpedia

    INDEX
    Explanations

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TestCase
    -0.06
     Х
    -0.06
    Console
    -0.06
     parameters
    -0.06
    >>↵
    -0.06
    Address
    -0.06
     console
    -0.06
     revive
    -0.06
     welfare
    -0.06
     aging
    -0.06
    POSITIVE LOGITS
     τη
    0.07
    Winvalid
    0.07
     konus
    0.07
     =================================
    0.06
    orld
    0.06
     �
    0.06
     LinearLayoutManager
    0.06
    esseract
    0.06
    ffd
    0.06
     ########################
    0.06
    Act Density 0.002%

    No Known Activations