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

    Neuronpedia

    INDEX
    Explanations

    clothing, activities, and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     monolithic
    0.47
     critic
    0.45
    clean
    0.40
    攏
    0.40
     बु
    0.40
     شوف
    0.40
     نصب
    0.38
    todo
    0.38
     establishing
    0.38
    handedly
    0.38
    POSITIVE LOGITS
    0.50
     Dolomites
    0.49
    짤
    0.49
    嶂
    0.48
    Metaxy
    0.47
     Fakult
    0.46
     Cervantes
    0.46
    hü
    0.46
    த்தை
    0.46
    शै
    0.45
    Act Density 0.000%

    No Known Activations