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

    Neuronpedia

    INDEX
    Explanations

    mobilization and engagement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proletariat
    0.68
     Comrade
    0.67
     Marxist
    0.65
     marx
    0.65
     comrade
    0.64
     capitalist
    0.64
     bourgeoisie
    0.63
     revolutionary
    0.62
     comrades
    0.61
     praxis
    0.60
    POSITIVE LOGITS
    Campus
    0.50
     सुनीता
    0.49
    Aire
    0.46
    िरी
    0.46
    Initially
    0.45
    校园
    0.45
    Pride
    0.45
    Brad
    0.45
     actief
    0.45
     कैंपस
    0.44
    Act Density 0.004%

    No Known Activations