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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VOID
    -0.08
     SUMMARY
    -0.07
    -spinner
    -0.06
     предвар
    -0.06
    _AG
    -0.06
     обов
    -0.06
     срав
    -0.06
    -Mart
    -0.06
     Backbone
    -0.06
    例如
    -0.06
    POSITIVE LOGITS
     itertools
    0.07
     enrolled
    0.06
    	build
    0.06
     enlisted
    0.06
     giov
    0.06
     Incredible
    0.06
     Kepler
    0.06
     Lou
    0.06
     belonged
    0.06
    fell
    0.05
    Act Density 0.036%

    No Known Activations