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

    Neuronpedia

    INDEX
    Explanations

    Indian states and culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?!?
    0.97
    ?!?!
    0.91
     یورپی
    0.80
     mutable
    0.78
     geologic
    0.77
    স্পষ্ট
    0.75
    entieth
    0.74
    pictured
    0.74
     transcendent
    0.73
     পেছন
    0.71
    POSITIVE LOGITS
     sarees
    1.90
     Maharashtra
    1.90
     till
    1.88
     lakh
    1.86
     Andhra
    1.84
     Haryana
    1.80
     Karnataka
    1.77
     saree
    1.76
     Odisha
    1.75
     upto
    1.74
    Act Density 0.083%

    No Known Activations