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

    Neuronpedia

    INDEX
    Explanations

    groups of people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _train
    -0.07
    啮
    -0.07
    'elle
    -0.07
     honored
    -0.07
     przec
    -0.06
     except
    -0.06
    拼多多
    -0.06
    日报道
    -0.06
     {↵
    -0.06
    iosa
    -0.06
    POSITIVE LOGITS
     Removes
    0.07
    董事会
    0.07
     downloadable
    0.07
     galleries
    0.07
    logen
    0.07
     gep
    0.07
    	atomic
    0.07
    libraries
    0.06
     loft
    0.06
     conspiracy
    0.06
    Act Density 0.103%

    No Known Activations