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

    Neuronpedia

    INDEX
    Explanations

    government

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kung
    -0.09
     Aunt
    -0.09
    爸爸
    -0.08
     UCLA
    -0.08
     craze
    -0.08
     Dara
    -0.08
     Isa
    -0.08
     Rim
    -0.08
    ilist
    -0.08
     Rasmussen
    -0.08
    POSITIVE LOGITS
    -sponsored
    0.13
    -funded
    0.11
    -appointed
    0.11
    -owned
    0.10
     tarafından
    0.09
    -approved
    0.09
     agencies
    0.09
     officials
    0.09
     affairs
    0.09
     Affairs
    0.09
    Act Density 0.025%

    No Known Activations