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

    Neuronpedia

    INDEX
    Explanations

    Welsh and Celtic languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дово
    0.47
     много
    0.44
     Steuer
    0.42
     воро
    0.42
     Акча
    0.42
    놁
    0.41
     равно
    0.41
    Анд
    0.41
    0.41
     aborted
    0.40
    POSITIVE LOGITS
     gyda
    0.73
     hefyd
    0.71
     cy
    0.70
    Cy
    0.69
     ym
    0.67
     gy
    0.64
     Cy
    0.63
     gyd
    0.63
     yn
    0.62
     Cym
    0.61
    Act Density 0.001%

    No Known Activations