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

    Neuronpedia

    INDEX
    Explanations

    letters, numbers, and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.47
    م
    0.47
    ா
    0.45
    ا
    0.45
    ం
    0.43
    ק
    0.41
    क
    0.40
    信息
    0.39
    त
    0.39
    a
    0.39
    POSITIVE LOGITS
    F
    0.45
     for
    0.42
    of
    0.40
    8
    0.39
     पाँच
    0.38
     ไม่
    0.38
     जाँच
    0.38
    E
    0.38
    Y
    0.38
     deux
    0.37
    Act Density 1.207%

    No Known Activations