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

    Neuronpedia

    INDEX
    Explanations

    temporarily enabling, disabling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    敬请
    -0.08
     Parade
    -0.08
     صباح
    -0.07
    Parse
    -0.07
    综合整治
    -0.07
     Communications
    -0.07
    ultural
    -0.07
    峙
    -0.07
     конкурс
    -0.07
    _hierarchy
    -0.07
    POSITIVE LOGITS
    .project
    0.08
    	default
    0.07
     predicted
    0.07
    Incorrect
    0.06
    (ret
    0.06
    秘诀
    0.06
    ])/
    0.06
    .total
    0.06
     {}\
    0.06
     derived
    0.06
    Act Density 0.088%

    No Known Activations