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

    Neuronpedia

    INDEX
    Explanations

    advanced and end-to-end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अड्
    0.95
    alten
    0.92
    েবের
    0.92
    仴
    0.90
    Zie
    0.89
    Letters
    0.88
    Exact
    0.87
     बाबू
    0.85
     impec
    0.85
    hood
    0.83
    POSITIVE LOGITS
     تحقیق
    0.87
    [@
    0.73
     تحقیقات
    0.68
     ricerche
    0.68
     उपयोगकर्ताओं
    0.66
    ))),
    0.66
     fusión
    0.66
     مار
    0.66
    ])
    0.65
     सुविधाओं
    0.65
    Act Density 0.108%

    No Known Activations