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

    Neuronpedia

    INDEX
    Explanations

    Data processing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    保
    -0.07
     Ruiz
    -0.07
    Decimal
    -0.07
     bedroom
    -0.07
    际
    -0.07
     training
    -0.06
     Crusher
    -0.06
     Reeves
    -0.06
    考虑
    -0.06
     nar
    -0.06
    POSITIVE LOGITS
    ×</
    0.07
     الكتاب
    0.07
    �
    0.06
     imgs
    0.06
    graf
    0.06
    553
    0.06
    �
    0.06
     userManager
    0.06
    .presentation
    0.06
     shm
    0.06
    Act Density 0.039%

    No Known Activations