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

    Neuronpedia

    INDEX
    Explanations

    PM welfare India

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chandigarh
    0.56
     Raipur
    0.56
     Chhattisgarh
    0.55
     Delhi
    0.54
     Jharkhand
    0.54
    Delhi
    0.53
     Bollywood
    0.52
     Bengaluru
    0.48
     IIT
    0.48
     Gurgaon
    0.48
    POSITIVE LOGITS
     Gare
    0.45
     মুদ্রা
    0.42
     डिवा
    0.40
     gare
    0.40
     MOD
    0.40
     PM
    0.39
    ناة
    0.39
     Pm
    0.39
     Lagrangian
    0.38
    렉
    0.38
    Act Density 0.002%

    No Known Activations