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

    Neuronpedia

    INDEX
    Explanations

    multiple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    یشه
    -0.08
     اچ
    -0.08
     günst
    -0.08
    дат
    -0.08
     wint
    -0.08
    akanan
    -0.08
    ристиан
    -0.08
    ога
    -0.08
    shops
    -0.08
    кт
    -0.07
    POSITIVE LOGITS
     rivalry
    0.09
    Duplicate
    0.09
     friendship
    0.09
     partnership
    0.08
    Allow
    0.08
     Duplicate
    0.08
     duplicates
    0.08
     redundancy
    0.08
     repeating
    0.08
    !?
    0.08
    Act Density 0.013%

    No Known Activations