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

    Neuronpedia

    INDEX
    Explanations

    date and time stamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     felt
    -1.13
     feel
    -1.07
     his
    -1.02
     only
    -1.01
     one
    -1.01
     in
    -0.97
     under
    -0.96
     until
    -0.95
     going
    -0.94
    ^*
    -0.94
    POSITIVE LOGITS
    那时
    1.09
    낵
    1.06
    ﺐ
    1.04
    那时候
    1.02
     cortesía
    1.02
     régulièrement
    1.02
     Lesnar
    1.02
     exactement
    1.01
    ovna
    1.00
     Donetsk
    0.99
    Act Density 0.046%

    No Known Activations