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

    Neuronpedia

    INDEX
    Explanations

    addition problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     новых
    -0.08
     personal
    -0.08
     destinée
    -0.08
    гр
    -0.08
     nouvelles
    -0.07
     ознаком
    -0.07
     появляется
    -0.07
     объяв
    -0.07
    онят
    -0.07
     governs
    -0.07
    POSITIVE LOGITS
     emprést
    0.08
     quotient
    0.08
     créditos
    0.08
     credito
    0.08
    ERCENT
    0.07
     crédito
    0.07
     Baseball
    0.07
    'imp
    0.07
    👏
    0.07
    Dial
    0.07
    Act Density 0.037%

    No Known Activations