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

    Neuronpedia

    INDEX
    Explanations

    drilled holes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    逦
    0.39
    CMAKE
    0.38
    डीसी
    0.37
    имо
    0.37
    អ
    0.36
     प्रमा
    0.35
    勮
    0.35
    வைப்
    0.35
    놁
    0.35
     ನ್ಯಾಯ
    0.35
    POSITIVE LOGITS
     holes
    2.39
     hole
    2.16
     Holes
    2.09
    holes
    1.90
     отверсти
    1.87
     Hole
    1.85
     drilled
    1.72
    hole
    1.70
    穴
    1.70
     drilling
    1.64
    Act Density 0.021%

    No Known Activations