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

    Neuronpedia

    INDEX
    Explanations

    conclusions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     magistrate
    -0.07
     excellence
    -0.06
     Avenue
    -0.06
     history
    -0.06
     granddaughter
    -0.06
     rue
    -0.06
     provision
    -0.06
     Orders
    -0.06
     khoán
    -0.06
     repetition
    -0.06
    POSITIVE LOGITS
     conclusions
    0.10
     conclusion
    0.08
     вывод
    0.08
     نتیجه
    0.07
    ipated
    0.06
     decision
    0.06
     чин
    0.06
    (ra
    0.06
    (opt
    0.06
     seizing
    0.06
    Act Density 0.011%

    No Known Activations