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

    Neuronpedia

    INDEX
    Explanations

    Rousseau and Locke

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pylint
    -0.08
    qa
    -0.08
     avion
    -0.08
     itertools
    -0.08
     timedelta
    -0.08
     inexp
    -0.08
     incur
    -0.07
     ail
    -0.07
    pytest
    -0.07
     Grammy
    -0.07
    POSITIVE LOGITS
     pamph
    0.09
     Locke
    0.08
     संविधान
    0.08
    提出
    0.08
    <File
    0.08
     हथ
    0.08
    אות
    0.08
     monarchy
    0.08
     trustees
    0.08
     Rousse
    0.08
    Act Density 0.003%

    No Known Activations