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

    Neuronpedia

    INDEX
    Explanations

    restatement of information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     st
    0.58
     স্ট
    0.52
     ಸ್ಟ
    0.52
     ST
    0.50
     ஸ்ட
    0.50
     St
    0.50
     اسٹ
    0.48
     Сто
    0.47
     Sta
    0.47
     स्‍ट
    0.47
    POSITIVE LOGITS
    ate
    1.04
    ates
    0.89
    ATE
    0.84
    atem
    0.82
    aten
    0.80
    at
    0.79
    aters
    0.76
    atet
    0.76
    ATES
    0.75
    āt
    0.74
    Act Density 0.006%

    No Known Activations