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

    Neuronpedia

    INDEX
    Explanations

    003

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minds
    -0.07
    .STATUS
    -0.06
    .setView
    -0.06
    Feels
    -0.06
    监听页面
    -0.06
     skepticism
    -0.06
    hpp
    -0.06
    ReceiveProps
    -0.06
    πως
    -0.06
     Paulo
    -0.06
    POSITIVE LOGITS
     contributions
    0.07
     Estr
    0.07
     Medal
    0.06
     ass
    0.06
     ==↵
    0.06
     işe
    0.06
    Bài
    0.06
     zákona
    0.06
    산
    0.06
    연
    0.06
    Act Density 0.004%

    No Known Activations