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

    Neuronpedia

    INDEX
    Explanations

    president

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    445
    -0.07
     Fantasy
    -0.07
    07
    -0.06
     onHide
    -0.06
    ườn
    -0.06
     whenever
    -0.06
    08
    -0.06
     semanas
    -0.06
    compat
    -0.06
    43
    -0.06
    POSITIVE LOGITS
     President
    0.10
    -President
    0.09
     president
    0.09
    President
    0.09
     presidente
    0.09
    -president
    0.08
    ，现在
    0.07
    atat
    0.07
     presidency
    0.07
    .getAbsolutePath
    0.07
    Act Density 0.025%

    No Known Activations