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

    Neuronpedia

    INDEX
    Explanations

    concentration of power and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rocky
    0.36
    บค้น
    0.36
     macOS
    0.36
     composants
    0.35
     Wirk
    0.35
     aktive
    0.35
     charakter
    0.35
     isom
    0.34
     verwenden
    0.34
     Klin
    0.33
    POSITIVE LOGITS
     profite
    0.70
     monopolies
    0.67
     финанси
    0.65
     bureaucratic
    0.63
     bureaucrats
    0.62
    壟
    0.61
     bureaucracy
    0.59
     lucrative
    0.58
     capitalist
    0.58
     profits
    0.56
    Act Density 0.175%

    No Known Activations