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

    Neuronpedia

    INDEX
    Explanations

    accessing object attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.67
    ت
    0.61
    т
    0.59
    G
    0.59
     gode
    0.52
    ی
    0.52
    W
    0.51
    ik
    0.51
    at
    0.50
    T
    0.50
    POSITIVE LOGITS
     of
    0.58
    0.57
     प्रतिशत
    0.39
    of
    0.39
     ऊ
    0.38
    ния
    0.38
     ensues
    0.37
    annya
    0.37
    ↵↵
    0.36
     ४
    0.36
    Act Density 0.000%

    No Known Activations