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

    Neuronpedia

    INDEX
    Explanations

    later

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zhao
    -0.07
     Io
    -0.06
     Stephan
    -0.06
     Comm
    -0.06
     varies
    -0.06
    Jobs
    -0.06
    .Mongo
    -0.06
     Blockchain
    -0.06
     MediaQuery
    -0.06
    ales
    -0.06
    POSITIVE LOGITS
    選択
    0.07
     उसक
    0.07
    からの
    0.07
    .cleanup
    0.07
    .decrypt
    0.07
     ┃
    0.06
     تلویزی
    0.06
    sar
    0.06
    _->
    0.06
    ../../
    0.06
    Act Density 0.005%

    No Known Activations