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

    Neuronpedia

    INDEX
    Explanations

    references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    terminate
    -0.07
     ®
    -0.07
    ?>/
    -0.07
     jaz
    -0.06
    monthly
    -0.06
     ăn
    -0.06
    smart
    -0.06
    σετε
    -0.06
    -0.06
    ीट
    -0.06
    POSITIVE LOGITS
    OfDay
    0.06
     Bài
    0.06
     образ
    0.06
    (className
    0.06
    (Address
    0.06
    ccion
    0.06
    Compile
    0.06
     عاش
    0.06
     См
    0.06
     Sor
    0.06
    Act Density 0.012%

    No Known Activations