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

    Neuronpedia

    INDEX
    Explanations

    systems and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Agricult
    0.72
     алкого
    0.71
    watercolor
    0.70
    Trav
    0.70
    ភាព
    0.67
    grpc
    0.67
    Oliver
    0.66
    Poker
    0.65
    То
    0.65
    Agricultural
    0.64
    POSITIVE LOGITS
     system
    1.57
     systems
    1.46
     program
    1.36
     programs
    1.26
     programma
    1.25
     시스템
    1.17
    システム
    1.14
     systeem
    1.13
     système
    1.13
     programme
    1.12
    Act Density 0.644%

    No Known Activations