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

    Neuronpedia

    INDEX
    Explanations

    Causes and reasons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NSK
    -0.08
     fav
    -0.08
    פט
    -0.07
    었
    -0.07
    🇯
    -0.07
     shooters
    -0.07
    గ
    -0.07
     Specs
    -0.07
    �
    -0.07
    惭
    -0.07
    POSITIVE LOGITS
     hora
    0.08
    Sie
    0.07
     resultados
    0.07
     И
    0.07
     conversions
    0.07
     Skywalker
    0.07
    Nguồn
    0.07
    -Christian
    0.07
    -menu
    0.07
     Routing
    0.07
    Act Density 0.058%

    No Known Activations