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

    Neuronpedia

    INDEX
    Explanations

    political coalitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shooters
    -0.08
    ingular
    -0.08
    <=
    -0.07
    𫠊
    -0.07
     Singular
    -0.07
    üler
    -0.07
    粒子
    -0.07
    生素
    -0.07
     characterize
    -0.06
     {...
    -0.06
    POSITIVE LOGITS
    蔡
    0.07
    תום
    0.07
     committing
    0.07
     מהמ
    0.07
    \">
    0.07
     lips
    0.07
    携手
    0.07
     proclaim
    0.06
    مواف
    0.06
    istributions
    0.06
    Act Density 0.013%

    No Known Activations