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

    Neuronpedia

    INDEX
    Explanations

    positive preamble to a question or idea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    0.30
    '{
    0.29
    ς
    0.29
     није
    0.27
    需
    0.27
    of
    0.26
    ।”
    0.26
    ।"
    0.26
    ’
    0.25
    uv
    0.25
    POSITIVE LOGITS
    erweise
    0.34
     for
    0.34
    لي
    0.31
     idea
    0.31
    ulously
    0.30
     craftsmanship
    0.29
     workmanship
    0.29
     job
    0.28
     stewardship
    0.28
     rhythm
    0.28
    Act Density 0.216%

    No Known Activations