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

    Neuronpedia

    INDEX
    Explanations

    Gen Z and Z-starting words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鍗
    0.39
    माष्टमी
    0.33
    ឃ
    0.32
    ព្រ
    0.32
    Ⲡ
    0.31
    ौसी
    0.31
    徙
    0.31
    闱
    0.31
    𒉌
    0.30
    ட்க
    0.30
    POSITIVE LOGITS
     Z
    4.53
    Z
    3.77
     z
    3.44
     З
    3.41
     الز
    3.09
    Ｚ
    3.03
     ز
    2.94
     Ζ
    2.77
    𝑍
    2.64
    З
    2.52
    Act Density 0.114%

    No Known Activations