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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doInBackground
    -0.07
     uttered
    -0.06
     ingress
    -0.06
     أخ
    -0.06
    �
    -0.06
    xffffff
    -0.06
    unitOfWork
    -0.06
     streamed
    -0.06
    Junior
    -0.06
    607
    -0.06
    POSITIVE LOGITS
     decades
    0.07
    릴
    0.07
     Money
    0.07
    money
    0.07
     stay
    0.07
     Blast
    0.07
     محافظ
    0.06
    kili
    0.06
    بي
    0.06
     Been
    0.06
    Act Density 0.011%

    No Known Activations