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

    Neuronpedia

    INDEX
    Explanations

    relentless focus on urban, combat, biological, career

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    brandt
    0.47
     civiles
    0.45
     wooden
    0.44
     monolithic
    0.43
     empires
    0.39
     alphabet
    0.39
     testimon
    0.39
    innt
    0.39
     command
    0.39
     jurid
    0.39
    POSITIVE LOGITS
     Karma
    0.41
     thải
    0.41
     LO
    0.40
     понадоби
    0.40
     तभी
    0.39
     Biodiversity
    0.39
     Trên
    0.38
     Rare
    0.38
     Costs
    0.38
     Donation
    0.37
    Act Density 0.001%

    No Known Activations