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

    Neuronpedia

    INDEX
    Explanations

    biggest strength or achievement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     things
    1.12
     thing
    1.08
     part
    1.02
     aspects
    0.98
     Things
    0.96
    Things
    0.94
     parts
    0.93
     portion
    0.92
     Dinge
    0.89
     factors
    0.88
    POSITIVE LOGITS
     preoccupation
    0.90
     появления
    0.85
     foes
    0.80
     preoccup
    0.78
     waking
    0.78
     foray
    0.76
    Accom
    0.75
     pursuits
    0.75
     contemporaries
    0.75
     compatriots
    0.75
    Act Density 0.072%

    No Known Activations