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

    Neuronpedia

    INDEX
    Explanations

    supern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _relationship
    -0.07
     TRANSACTION
    -0.07
     Wasser
    -0.06
     connected
    -0.06
     phá
    -0.06
    ーマ
    -0.06
    项目
    -0.06
    _prod
    -0.06
     نگهد
    -0.06
     Different
    -0.06
    POSITIVE LOGITS
     supern
    0.09
    .ToInt
    0.08
    lomou
    0.07
     supreme
    0.07
     bekannt
    0.06
    uels
    0.06
    unded
    0.06
     는
    0.06
    .GetInt
    0.06
    κας
    0.06
    Act Density 0.002%

    No Known Activations