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

    Neuronpedia

    INDEX
    Explanations

    tasks and client interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ন
    0.99
    s
    0.90
    n
    0.81
    6
    0.79
     runApp
    0.78
    9
    0.77
     d
    0.77
    Sir
    0.75
    7
    0.73
    kafka
    0.72
    POSITIVE LOGITS
    ى
    0.91
    يين
    0.85
     envision
    0.82
     Ciência
    0.82
    이에
    0.80
     escenarios
    0.80
     فيما
    0.79
    柩
    0.79
     وفي
    0.77
    𝔀
    0.77
    Act Density 0.001%

    No Known Activations