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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ())↵↵
    -0.06
    andering
    -0.06
    刑
    -0.06
     instructor
    -0.06
    Drop
    -0.06
    ец
    -0.06
    ляем
    -0.06
    _mock
    -0.06
    structor
    -0.06
     sediment
    -0.06
    POSITIVE LOGITS
     گروه
    0.08
     AO
    0.07
     стос
    0.07
     WH
    0.06
     Palo
    0.06
    етерб
    0.06
     melhores
    0.06
    κλη
    0.06
     analý
    0.06
    ヨ
    0.06
    Act Density 0.049%

    No Known Activations