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

    Neuronpedia

    INDEX
    Explanations

    multi-script and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hvis
    0.93
     børn
    0.88
     når
    0.86
     vacanam
    0.84
     svaki
    0.83
     jeśli
    0.81
     ungdom
    0.81
     dvije
    0.81
     simonsen
    0.81
     produkter
    0.80
    POSITIVE LOGITS
     در
    1.02
     به
    1.02
     و
    0.90
     از
    0.90
     را
    0.86
     می
    0.84
    0.82
     شده
    0.82
     خود
    0.79
    IN
    0.76
    Act Density 0.001%

    No Known Activations