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

    Neuronpedia

    INDEX
    Explanations

    solving math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perifer
    -0.09
    Older
    -0.08
    واد
    -0.08
     ]];
    -0.08
     sometime
    -0.08
     coisas
    -0.08
    柄
    -0.08
     chcete
    -0.08
    ்ம
    -0.07
     interessa
    -0.07
    POSITIVE LOGITS
     gcd
    0.10
     elimination
    0.08
     deduction
    0.08
     eliminates
    0.08
     arithmetic
    0.08
    (arr
    0.08
     algebra
    0.07
     Ded
    0.07
    (nums
    0.07
     digits
    0.07
    Act Density 0.068%

    No Known Activations