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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ci
    -0.06
    aurant
    -0.06
    -store
    -0.06
     headphone
    -0.06
     ژوئ
    -0.06
    िसस
    -0.06
    _ma
    -0.06
    	se
    -0.06
     استرات
    -0.06
    _box
    -0.06
    POSITIVE LOGITS
    арамет
    0.06
    _subscribe
    0.06
    	document
    0.06
    іж
    0.06
    ้ง
    0.06
    213
    0.06
    зд
    0.06
    hints
    0.06
     Jesse
    0.06
     приводит
    0.06
    Act Density 0.343%

    No Known Activations