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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    课程
    -0.06
     Commander
    -0.06
     deadlock
    -0.06
     Cemetery
    -0.06
    отов
    -0.06
     東
    -0.06
     всего
    -0.06
    الص
    -0.06
    levelname
    -0.06
     Introduction
    -0.06
    POSITIVE LOGITS
     khối
    0.06
    spread
    0.06
    �
    0.06
     měsíců
    0.06
    touch
    0.06
     زر
    0.06
    (master
    0.06
     지
    0.06
     đo
    0.06
     Jessie
    0.06
    Act Density 0.001%

    No Known Activations