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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ube
    -0.06
    áy
    -0.06
    预览
    -0.06
    اسم
    -0.06
    .phone
    -0.06
    OUTPUT
    -0.06
     установ
    -0.06
     Tại
    -0.06
    ANGED
    -0.06
     praised
    -0.05
    POSITIVE LOGITS
    acio
    0.06
     [_
    0.06
    ￣￣
    0.06
     ￣
    0.06
     rejection
    0.06
     Modifier
    0.06
     يا
    0.06
    (norm
    0.06
    गर
    0.06
    verb
    0.06
    Act Density 0.073%

    No Known Activations