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

    Neuronpedia

    INDEX
    Explanations

    compression/decompression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vých
    -0.06
    AK
    -0.06
    akers
    -0.06
    \xd
    -0.06
    illage
    -0.06
     makers
    -0.06
     BMP
    -0.06
    िध
    -0.06
    池
    -0.06
     яке
    -0.06
    POSITIVE LOGITS
     invit
    0.06
    不同
    0.06
     Story
    0.06
     invo
    0.06
    __':
↵
    0.06
    umed
    0.06
     getObject
    0.06
     mentioning
    0.06
     Stadium
    0.06
    (nx
    0.06
    Act Density 0.039%

    No Known Activations