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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    واع
    -0.06
     طراحی
    -0.06
    =((
    -0.06
     seins
    -0.06
    含
    -0.06
     <>
    -0.06
     afin
    -0.06
     非
    -0.06
    ываем
    -0.06
    اتف
    -0.06
    POSITIVE LOGITS
    response
    0.07
    trieve
    0.06
    ámara
    0.06
    revolution
    0.06
    €
    0.06
     »,
    0.06
    歐
    0.06
     ArrayCollection
    0.06
     thuyết
    0.06
    ousse
    0.06
    Act Density 0.101%

    No Known Activations