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

    Neuronpedia

    INDEX
    Explanations

    conclusion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MustCompile
    -0.07
    /chart
    -0.07
    CustomerId
    -0.07
     stride
    -0.07
     والف
    -0.07
     עצמ
    -0.06
     Mp
    -0.06
    自我
    -0.06
    ଌ
    -0.06
    _amp
    -0.06
    POSITIVE LOGITS
    зов
    0.09
     later
    0.08
    token
    0.08
    persons
    0.07
    遗迹
    0.07
     Bangkok
    0.07
    .transparent
    0.07
    nodes
    0.07
     cron
    0.07
    .gridColumn
    0.07
    Act Density 0.011%

    No Known Activations