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

    Neuronpedia

    INDEX
    Explanations

    ; model ; the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neurologic
    1.03
     dramatically
    0.97
     pennies
    0.96
     nonfiction
    0.91
     <--
    0.90
    Oregon
    0.89
     તેણી
    0.89
     または
    0.87
     inexpensive
    0.86
    potentially
    0.85
    POSITIVE LOGITS
     Hence
    2.17
    Hence
    1.99
     hence
    1.79
     till
    1.67
     lakh
    1.67
     upto
    1.65
     atleast
    1.61
    Till
    1.61
     Bengaluru
    1.61
     Hyderabad
    1.59
    Act Density 0.031%

    No Known Activations