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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    West
    -0.07
    .Contains
    -0.07
    deep
    -0.07
     hike
    -0.07
     West
    -0.07
    oy
    -0.07
    Nit
    -0.07
     storytelling
    -0.07
    Rus
    -0.07
    İR
    -0.07
    POSITIVE LOGITS
    	usage
    0.07
    ]))↵↵
    0.06
    }}],↵
    0.06
     flock
    0.06
    有效
    0.06
    -j
    0.06
    .Loader
    0.06
     newly
    0.06
    烧
    0.06
    =b
    0.06
    Act Density 0.012%

    No Known Activations