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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '}
    -0.06
     एम
    -0.06
    影響
    -0.06
    ngthen
    -0.06
    .DataAnnotations
    -0.06
     الع
    -0.05
     смог
    -0.05
     Boulder
    -0.05
    (cn
    -0.05
     زیست
    -0.05
    POSITIVE LOGITS
     contradictions
    0.07
     cinematic
    0.07
    TXT
    0.07
     taped
    0.07
     instrumentation
    0.07
    OfWork
    0.07
     swaps
    0.07
    Start
    0.07
    imeters
    0.07
    _sequence
    0.06
    Act Density 0.001%

    No Known Activations