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

    Neuronpedia

    INDEX
    Explanations

    increasing attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     største
    0.47
     petite
    0.44
     поне
    0.43
     Largest
    0.41
     пропуска
    0.41
     наиболь
    0.40
    ):["
    0.40
     //[
    0.39
     /**
    0.39
     قلنا
    0.39
    POSITIVE LOGITS
     Ameri
    0.40
     Minnesota
    0.39
     Amer
    0.39
     Pitt
    0.37
     future
    0.36
     Acer
    0.36
     Copeland
    0.36
    ợi
    0.36
     biochem
    0.35
     Wisconsin
    0.35
    Act Density 0.001%

    No Known Activations