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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     филь
    -0.08
    807
    -0.07
    argas
    -0.06
    يدي
    -0.06
    datasets
    -0.06
     CLOCK
    -0.06
     что
    -0.06
    some
    -0.06
     crafted
    -0.06
     poru
    -0.06
    POSITIVE LOGITS
     distracted
    0.06
     Cheese
    0.06
    iêu
    0.06
    访
    0.06
    iat
    0.06
     penetration
    0.06
     necessário
    0.06
     Cure
    0.06
    ubs
    0.06
     propagation
    0.06
    Act Density 0.004%

    No Known Activations