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

    Neuronpedia

    INDEX
    Explanations

    Javascript closures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     planning
    -0.09
     ASTM
    -0.09
     nose
    -0.08
     পরিকল্প
    -0.08
     योजना
    -0.08
     undertaken
    -0.08
     стандар
    -0.08
     Diplom
    -0.08
     hekt
    -0.08
     Planning
    -0.08
    POSITIVE LOGITS
     partagé
    0.10
     શેર
    0.10
    共享
    0.10
    泄
    0.09
     inaccessible
    0.09
    分享
    0.09
    访问
    0.09
    陷
    0.09
     enclosing
    0.09
    SH
    0.09
    Act Density 0.003%

    No Known Activations