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

    Neuronpedia

    INDEX
    Explanations

    sum

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bracketing
    0.72
    Elite
    0.70
    庿
    0.69
    DUC
    0.68
     ۋە
    0.67
     Elite
    0.66
    मीटर
    0.63
    School
    0.63
     actuator
    0.63
     Zimbabwean
    0.62
    POSITIVE LOGITS
     sum
    0.83
    Sum
    0.79
    sum
    0.74
     sums
    0.66
     Sum
    0.65
    头上
    0.65
    டத்தில்
    0.63
     summation
    0.62
    Sums
    0.61
     hand
    0.61
    Act Density 0.085%

    No Known Activations