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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Celebrity
    -0.09
     التواصل
    -0.09
     Movies
    -0.09
     hust
    -0.09
     వే�
    -0.08
     నిర్వహ
    -0.08
    挣
    -0.08
    欣
    -0.08
     alguém
    -0.08
     everyone
    -0.08
    POSITIVE LOGITS
     treaty
    0.15
     clauses
    0.15
     amendments
    0.14
     cláus
    0.13
     lawmakers
    0.13
     legislative
    0.13
     repeal
    0.12
     clause
    0.12
     provisions
    0.12
     drafting
    0.12
    Act Density 0.077%

    No Known Activations