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

    Neuronpedia

    INDEX
    Explanations

    numerical word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Enums
    -0.08
    baixo
    -0.07
     જૂ
    -0.07
    ிந
    -0.07
     આવા
    -0.07
     நீ
    -0.07
    -0.07
    agon
    -0.07
    �
    -0.07
     এমন
    -0.07
    POSITIVE LOGITS
     winnings
    0.11
     ಸೇರ
    0.10
     acquisitions
    0.10
     плюс
    0.10
     influx
    0.10
     accrued
    0.09
     accumulation
    0.09
     birthdays
    0.09
     accumulator
    0.09
     mergers
    0.09
    Act Density 0.032%
    No Known Activations