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

    Neuronpedia

    INDEX
    Explanations

    pronouns and power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hlung
    0.50
    Semester
    0.49
    semester
    0.49
    streamlit
    0.47
     plasmids
    0.46
    chainId
    0.46
     estimated
    0.44
    osomes
    0.43
    CO
    0.43
    Calcium
    0.42
    POSITIVE LOGITS
    同様
    0.49
     остальные
    0.43
    不允许
    0.42
     ሌሎች
    0.41
    爱好者
    0.41
     Bait
    0.41
     cropped
    0.41
     coupe
    0.40
     भजन
    0.40
     топ
    0.40
    Act Density 0.006%

    No Known Activations