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

    Neuronpedia

    INDEX
    Explanations

    returning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ടെ
    -0.09
    テ
    -0.08
     dik
    -0.08
     كأس
    -0.08
     ls
    -0.08
     interv
    -0.07
    提供
    -0.07
     테
    -0.07
     ther
    -0.07
     testi
    -0.07
    POSITIVE LOGITS
     desperation
    0.15
     desperate
    0.15
     desesper
    0.13
     predicament
    0.13
     желание
    0.11
     sighed
    0.11
    deadline
    0.11
     plight
    0.11
     craving
    0.10
     cravings
    0.10
    Act Density 0.034%

    No Known Activations