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

    Neuronpedia

    INDEX
    Explanations

    political power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     operands
    0.40
     manually
    0.35
     باستخدام
    0.34
     tuple
    0.34
     primitives
    0.33
     angular
    0.32
     whitespace
    0.32
     workspace
    0.32
     sprites
    0.32
     halftone
    0.31
    POSITIVE LOGITS
     políticos
    0.41
    政治
    0.39
     politiques
    0.38
     politische
    0.38
    political
    0.38
     politici
    0.38
    government
    0.37
     denunci
    0.35
     ხელისუფ
    0.35
     gobiernos
    0.34
    Act Density 3.234%

    No Known Activations