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

    Neuronpedia

    INDEX
    Explanations

    strategy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    841
    -0.07
     бы
    -0.06
     Corpus
    -0.06
    ẳ
    -0.06
     shard
    -0.06
     MPI
    -0.06
     `;↵
    -0.06
     ApplicationException
    -0.06
    ầ
    -0.06
     TString
    -0.06
    POSITIVE LOGITS
     HelloWorld
    0.06
    _about
    0.06
     車
    0.06
    upid
    0.06
    nex
    0.06
     Omni
    0.06
     cloak
    0.06
    Train
    0.06
     música
    0.06
    इसक
    0.06
    Act Density 0.000%

    No Known Activations