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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acknowled
    -0.06
     fs
    -0.06
    lobby
    -0.06
     Fé
    -0.06
    .total
    -0.06
    Dog
    -0.06
    소를
    -0.06
     ден
    -0.06
     aldı
    -0.06
    _null
    -0.06
    POSITIVE LOGITS
    ерами
    0.07
    ポ
    0.06
     reload
    0.06
    аніз
    0.06
     mük
    0.06
     itch
    0.06
    opa
    0.06
    инок
    0.06
    太郎
    0.06
     Almanya
    0.06
    Act Density 0.002%

    No Known Activations