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

    Neuronpedia

    INDEX
    Explanations

    drilling holes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    0.99
    ale
    0.91
    :
    0.89
    ні
    0.84
    alley
    0.84
    the
    0.84
    ต์
    0.78
    ﺲ
    0.76
    ди
    0.75
    t
    0.75
    POSITIVE LOGITS
     drills
    1.22
     drilled
    1.20
     holes
    1.19
     Drilling
    1.16
     Drill
    1.07
     ड्रिल
    1.03
     drilling
    1.02
     drill
    0.99
     отверсти
    0.93
    ה
    0.90
    Act Density 0.009%

    No Known Activations