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

    Neuronpedia

    INDEX
    Explanations

    nationalism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     winning
    -0.07
     उस
    -0.07
     mental
    -0.06
    収
    -0.06
     doGet
    -0.06
    ственное
    -0.06
    ATERIAL
    -0.06
     rodz
    -0.06
    �
    -0.06
    Ljava
    -0.06
    POSITIVE LOGITS
     nationalism
    0.10
     populist
    0.09
     nationalist
    0.09
     nationalists
    0.07
    Include
    0.06
    endent
    0.06
     Sequential
    0.06
    ivel
    0.06
    ulist
    0.06
     popul
    0.06
    Act Density 0.005%

    No Known Activations