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

    Neuronpedia

    INDEX
    Explanations

    sql if not exists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     regulations
    0.43
     regler
    0.40
     dlatego
    0.40
     ಸಮಯದಲ್ಲಿ
    0.39
    igenes
    0.39
    დესაც
    0.39
    instagram
    0.38
    )}+\
    0.38
    giveness
    0.38
    instances
    0.38
    POSITIVE LOGITS
     ஒலி
    0.44
    াড়া
    0.44
     колеба
    0.44
     这
    0.44
     изо
    0.44
     нау
    0.43
    довж
    0.43
    верса
    0.42
     dozen
    0.41
     कंपन
    0.41
    Act Density 0.001%

    No Known Activations