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

    Neuronpedia

    INDEX
    Explanations

    software licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utilization
    -0.07
     маль
    -0.06
     moeten
    -0.06
     memories
    -0.06
     ultrasound
    -0.06
     ammo
    -0.06
    遗
    -0.06
    ducible
    -0.06
     onPage
    -0.06
     BFS
    -0.06
    POSITIVE LOGITS
    /↵↵
    0.07
    TERS
    0.06
    OCK
    0.06
     bordel
    0.06
    avigate
    0.06
     updating
    0.06
    (ERR
    0.06
     il
    0.06
     damaging
    0.06
     ){↵↵
    0.06
    Act Density 0.001%

    No Known Activations