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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations/Sentence Start

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Customizer
    -0.08
    ,opt
    -0.08
     Styling
    -0.08
    赖
    -0.08
    .documentation
    -0.07
    采购
    -0.07
    优化
    -0.07
    chez
    -0.07
    :["
    -0.07
    =>{↵
    -0.07
    POSITIVE LOGITS
     protagonist
    0.09
     protagonists
    0.09
     protagonista
    0.08
     antagon
    0.08
     ঘটন
    0.08
     villain
    0.08
     Adolesc
    0.08
     கத
    0.08
     antagonist
    0.08
     Niemand
    0.08
    Act Density 0.084%

    No Known Activations