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

    Neuronpedia

    INDEX
    Explanations

    end of turn marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    importanza
    0.47
     നെറ്റ്‌വർ
    0.46
    ഷ്ട്ര
    0.46
    ocycl
    0.46
    駅
    0.46
     mergeddata
    0.45
    ὃ
    0.45
    ]*(
    0.44
    ścio
    0.44
    ⊖
    0.44
    POSITIVE LOGITS
     All
    0.51
     composer
    0.50
     source
    0.49
     typical
    0.49
     containing
    0.48
     contain
    0.45
     vetted
    0.45
     metagen
    0.45
     Sh
    0.44
     configuration
    0.44
    Act Density 0.000%

    No Known Activations