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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kỹ
    0.72
     मानें
    0.70
     Claims
    0.69
     ہوگا
    0.68
     Estimates
    0.68
    pare
    0.67
     نظر
    0.66
     claims
    0.65
     parameter
    0.64
     Ч
    0.62
    POSITIVE LOGITS
     visited
    1.06
     encountered
    1.04
     went
    1.03
     ran
    1.02
     faced
    1.02
     wanted
    0.98
     drove
    0.98
     didn
    0.95
     restarted
    0.94
     stumbled
    0.92
    Act Density 0.019%

    No Known Activations