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

    Neuronpedia

    INDEX
    Explanations

    bar and its continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    դ
    0.42
    ផល
    0.40
    Sure
    0.38
    0.38
    JUST
    0.38
    Tidak
    0.38
     gewährleisten
    0.38
    guided
    0.37
    據
    0.37
     SURE
    0.37
    POSITIVE LOGITS
    becue
    0.88
    celona
    0.78
    riers
    0.71
    唧
    0.64
     bar
    0.64
    ্ষিক
    0.62
    olome
    0.62
    Bar
    0.58
    itone
    0.57
    BAR
    0.57
    Act Density 0.024%

    No Known Activations