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

    Neuronpedia

    INDEX
    Explanations

    Intent, permissions, command, startId

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bodega
    0.51
     whiskey
    0.49
     groep
    0.45
     味
    0.44
     bourbon
    0.44
     obed
    0.44
     dans
    0.43
    шие
    0.42
     bilingual
    0.42
     moneda
    0.42
    POSITIVE LOGITS
    亣
    0.50
    on
    0.41
    ა
    0.41
    Packages
    0.40
     Mechanisms
    0.40
    EAST
    0.39
    िफिशियल
    0.39
     Harv
    0.39
     Championships
    0.39
     Models
    0.38
    Act Density 0.002%

    No Known Activations