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

    Neuronpedia

    INDEX
    Explanations

    Life-threatening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Đây
    -0.08
     Quiet
    -0.07
    roken
    -0.07
    anol
    -0.06
     Pavel
    -0.06
     AssemblyCopyright
    -0.06
    Modify
    -0.06
     Plantae
    -0.06
     ance
    -0.06
     $("
    -0.06
    POSITIVE LOGITS
    -threatening
    0.08
    istinguish
    0.07
     lifelong
    0.07
    )?↵↵
    0.07
    ..."↵↵
    0.07
     откры
    0.07
    /'↵
    0.07
    题
    0.06
     discovery
    0.06
    功能
    0.06
    Act Density 0.003%

    No Known Activations