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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rát
    -0.08
    火
    -0.07
    ленно
    -0.06
    ก
    -0.06
     Tro
    -0.06
    ası
    -0.06
    .Start
    -0.06
     Xml
    -0.06
    ूरत
    -0.06
     hale
    -0.06
    POSITIVE LOGITS
     чуж
    0.08
     //{
↵
    0.07
    *******
↵
    0.07
     downside
    0.06
    лений
    0.06
    366
    0.06
     WWW
    0.06
    @section
    0.06
    "]');↵
    0.06
    PMC
    0.06
    Act Density 0.126%

    No Known Activations