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

    Neuronpedia

    INDEX
    Explanations

    notification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _look
    -0.07
     Amsterdam
    -0.06
     legion
    -0.06
    Dead
    -0.06
     Пр
    -0.06
    jos
    -0.06
    _exam
    -0.06
     MSC
    -0.06
     δο
    -0.06
    έν
    -0.06
    POSITIVE LOGITS
    ницт
    0.08
    _representation
    0.07
    >[]
    0.07
    itioner
    0.07
    ….
    0.06
     عملی
    0.06
    タイ
    0.06
    .ToolStripMenuItem
    0.06
    -dev
    0.06
     sélection
    0.06
    Act Density 0.075%

    No Known Activations