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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lista
    -0.06
    it
    -0.06
    terminate
    -0.06
    σταν
    -0.06
     flows
    -0.06
     breeding
    -0.06
    	Command
    -0.06
     magazines
    -0.06
     Ernest
    -0.06
     discovering
    -0.06
    POSITIVE LOGITS
    auce
    0.06
    .poster
    0.06
    kbd
    0.06
    .md
    0.06
     rõ
    0.06
    racuse
    0.06
    383
    0.06
    _loc
    0.06
     citing
    0.06
    微软雅黑
    0.06
    Act Density 0.258%

    No Known Activations