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

    Neuronpedia

    INDEX
    Explanations

    poverty policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    分别
    -0.09
    oworld
    -0.08
    edo
    -0.08
     élèves
    -0.08
    ুষ্ঠ
    -0.08
    ylvania
    -0.08
    rica
    -0.07
    verify
    -0.07
    েনে
    -0.07
    山东
    -0.07
    POSITIVE LOGITS
     staffing
    0.09
     vouchers
    0.09
     ought
    0.08
     voucher
    0.08
     cibl
    0.08
     targeted
    0.08
     объяв
    0.08
     tide
    0.08
     bör
    0.08
     subpoena
    0.08
    Act Density 0.015%

    No Known Activations