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

    Neuronpedia

    INDEX
    Explanations

    primality test logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ("")
    0.44
    horse
    0.43
    erme
    0.41
    mare
    0.39
    ("
    0.37
    hor
    0.37
    ('')
    0.37
    )']
    0.36
     ("
    0.36
    givers
    0.35
    POSITIVE LOGITS
    قار
    0.40
     terrestre
    0.40
    厈
    0.38
    itura
    0.38
     Aş
    0.38
     synthase
    0.38
     ایکسپ
    0.38
     đị
    0.37
     razem
    0.37
     צו
    0.36
    Act Density 0.002%

    No Known Activations