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

    Neuronpedia

    INDEX
    Explanations

    materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eating
    -0.07
    ynchronization
    -0.07
     Fast
    -0.07
     dog
    -0.07
     실행
    -0.07
    uddled
    -0.06
    ocument
    -0.06
    Defs
    -0.06
    ควร
    -0.06
    ted
    -0.06
    POSITIVE LOGITS
     đất
    0.07
     intrigued
    0.06
     ebony
    0.06
    follow
    0.06
    金属
    0.06
     nylon
    0.06
    INavigation
    0.06
     copper
    0.06
     Ebony
    0.06
     rubble
    0.06
    Act Density 0.067%

    No Known Activations