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

    Neuronpedia

    INDEX
    Explanations

    Adult

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �로
    -0.07
    *a
    -0.07
    482
    -0.06
     Collector
    -0.06
    _masks
    -0.06
    Hal
    -0.06
    _console
    -0.06
     záv
    -0.06
    268
    -0.06
     practice
    -0.06
    POSITIVE LOGITS
     Mourinho
    0.06
     mám
    0.06
    相同
    0.06
     blankets
    0.06
     </>↵
    0.06
    絵
    0.06
    усти
    0.06
     hatte
    0.06
     servi
    0.06
     auditory
    0.06
    Act Density 0.021%

    No Known Activations