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

    Neuronpedia

    INDEX
    Explanations

    sequences after certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.09
    2
    1.09
    7
    1.02
    0
    1.02
    '
    1.00
    id
    0.98
    $\
    0.98
    5
    0.97
    8
    0.96
    9
    0.96
    POSITIVE LOGITS
     AMPK
    0.95
     AMOLED
    0.88
     Baylor
    0.84
    粡
    0.83
     sarcoma
    0.82
     delicios
    0.81
     clínicas
    0.80
     toxins
    0.80
     beter
    0.80
     átomos
    0.79
    Act Density 0.001%

    No Known Activations