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

    Neuronpedia

    INDEX
    Explanations

    ROS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reviews
    -0.06
    theory
    -0.06
    ekk
    -0.06
    ']="
    -0.06
     ΠΡ
    -0.06
     квад
    -0.06
     blockbuster
    -0.06
    ичних
    -0.06
    .lesson
    -0.06
     ›
    -0.05
    POSITIVE LOGITS
     procrast
    0.07
     Hier
    0.07
    .Here
    0.07
    anel
    0.06
     Assad
    0.06
     legally
    0.06
     Dub
    0.06
    -oriented
    0.06
     ケ
    0.06
     Gambling
    0.06
    Act Density 0.001%

    No Known Activations