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

    Neuronpedia

    INDEX
    Explanations

    academic citations and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">→</
    0.35
     দক্ষিণে
    0.35
    вах
    0.34
    бычно
    0.33
    ណៈ
    0.33
    lovl
    0.33
     евро
    0.32
     대신
    0.32
    вате
    0.32
    ណ្ឌ
    0.32
    POSITIVE LOGITS
    ind
    0.44
    we
    0.38
    ocken
    0.34
    0
    0.34
    ott
    0.33
     Orphan
    0.33
     Alzheimer
    0.32
    uz
    0.32
    ையைக்
    0.32
     eso
    0.32
    Act Density 0.000%

    No Known Activations