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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    煮
    -0.07
     Hơn
    -0.06
    一种
    -0.06
     Chocolate
    -0.06
    ilig
    -0.06
    水中
    -0.06
    贵族
    -0.06
     phrase
    -0.06
    民营企业
    -0.06
     raft
    -0.06
    POSITIVE LOGITS
    Extent
    0.07
     EXEC
    0.07
    시험
    0.07
    mdat
    0.07
    饬
    0.06
     실행
    0.06
    ?).
    0.06
    Attack
    0.06
    _play
    0.06
    .setViewportView
    0.06
    Act Density 0.035%

    No Known Activations