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

    Neuronpedia

    INDEX
    Explanations

    unique

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .baidu
    -0.07
     Battlefield
    -0.07
     ahead
    -0.07
    _cmd
    -0.07
    seed
    -0.07
     sedan
    -0.07
     Commands
    -0.06
    ้อน
    -0.06
     baz
    -0.06
     Deep
    -0.06
    POSITIVE LOGITS
    {o
    0.07
    冼
    0.06
    包容
    0.06
     ogląda
    0.06
     ори
    0.06
     Nora
    0.06
    と共
    0.06
     quà
    0.06
    լ
    0.06
     $↵
    0.06
    Act Density 0.005%

    No Known Activations